[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"$fh3-YoTC8VDjftrYLnx9RAAU3VyThwt9WM4o_PZYPOCA":3,"$f6lrJ8CSZA9jciXrJStfFDGQLy42Woin6yvAjxclYbIY":126,"$fMsGaq5AlICjBk2FRJcNCCEXj0ZXvh4flK1eKhsl2Te8":131},{"slug":4,"name":5,"version":6,"author":7,"author_profile":8,"description":9,"short_description":10,"active_installs":11,"downloaded":12,"rating":13,"num_ratings":14,"last_updated":15,"tested_up_to":16,"requires_at_least":17,"requires_php":18,"tags":19,"homepage":25,"download_link":26,"security_score":13,"vuln_count":27,"unpatched_count":27,"last_vuln_date":28,"fetched_at":29,"discovery_status":30,"vulnerabilities":31,"developer":32,"crawl_stats":28,"alternatives":39,"analysis":28,"fingerprints":28},"kp-agent-ready","KP Agent Ready","1.1.88","Kevin Pirnie","https:\u002F\u002Fprofiles.wordpress.org\u002Fkevp75\u002F","\u003Cp>AI agents — tools like ChatGPT, Claude, Copilot, and the growing ecosystem of autonomous AI systems — are increasingly being pointed at websites to gather information, interact with APIs, and perform tasks on behalf of users. For a site to work well with these agents, it needs to speak the right language: publishing structured discovery files, declaring its capabilities, and responding to agent-specific requests in the right format.\u003C\u002Fp>\n\u003Cp>\u003Cstrong>KP Agent Ready\u003C\u002Fstrong> handles all of that for your WordPress site. It implements the current set of agent-readiness standards and the broader AI agent ecosystem — without requiring you to manually create files, edit server configs, or touch a line of code. Everything is managed from a dedicated settings page in the WordPress admin.\u003C\u002Fp>\n\u003Ch4>What It Does\u003C\u002Fh4>\n\u003Cp>\u003Cstrong>RFC 8288 Link Response Headers\u003C\u002Fstrong>\u003Cbr \u002F>\nEvery response your site sends will include \u003Ccode>Link\u003C\u002Fcode> headers pointing agents to your API catalog, agent skills index, and MCP server card. This is how agents find your discovery documents without having to guess URLs.\u003C\u002Fp>\n\u003Cp>\u003Cstrong>API Catalog — \u003Ccode>\u002F.well-known\u002Fapi-catalog\u003C\u002Fcode>\u003C\u002Fstrong>\u003Cbr \u002F>\nPublishes a machine-readable catalog of your site’s APIs in the \u003Ccode>application\u002Flinkset+json\u003C\u002Fcode> format defined by RFC 9727. Each entry in the catalog can point to an OpenAPI specification, human-readable documentation, and a health\u002Fstatus endpoint. If you have not configured any entries yet, the plugin serves a sensible fallback automatically so the endpoint is always valid.\u003C\u002Fp>\n\u003Cp>\u003Cstrong>Agent Skills Index — \u003Ccode>\u002F.well-known\u002Fagent-skills\u002Findex.json\u003C\u002Fcode>\u003C\u002Fstrong>\u003Cbr \u002F>\nPublishes a skills discovery index per the Agent Skills Discovery RFC v0.2.0. This tells agents what your site can \u003Cem>do\u003C\u002Fem> — search your blog, browse your portfolio, submit a contact form, and so on.\u003C\u002Fp>\n\u003Cp>Skills are built from three sources:\u003C\u002Fp>\n\u003Cul>\n\u003Cli>\u003Cstrong>Blog articles\u003C\u002Fstrong> — a search skill and a browse skill, toggled with a single switch\u003C\u002Fli>\n\u003Cli>\u003Cstrong>Custom post types\u003C\u002Fstrong> — any public CPT registered on your site appears as a checkbox; tick it and it gets a browse skill pointing to its archive\u003C\u002Fli>\n\u003Cli>\u003Cstrong>Manual entries\u003C\u002Fstrong> — define any additional skill with a name, type, description, URL, and an optional sha256 digest\u003C\u002Fli>\n\u003C\u002Ful>\n\u003Cp>\u003Cstrong>MCP Server Card — \u003Ccode>\u002F.well-known\u002Fmcp\u002Fserver-card.json\u003C\u002Fcode>\u003C\u002Fstrong>\u003Cbr \u002F>\nPublishes an MCP Server Card (SEP-1649) identifying your site to Model Context Protocol clients. Configurable name, version, description, transport endpoint, and a capability list. If you do not have an MCP server running yet, just leave the transport blank — the card is still valid and useful for discovery.\u003C\u002Fp>\n\u003Cp>\u003Cstrong>OAuth \u002F OIDC Discovery — \u003Ccode>\u002F.well-known\u002Fopenid-configuration\u003C\u002Fcode> or \u003Ccode>\u002F.well-known\u002Foauth-authorization-server\u003C\u002Fcode>\u003C\u002Fstrong>\u003Cbr \u002F>\nIf your site exposes protected APIs that require authentication, this feature publishes the discovery metadata agents need to authenticate. Supports both OpenID Connect Discovery 1.0 and RFC 8414. Disabled by default — only enable it if you have the infrastructure in place.\u003C\u002Fp>\n\u003Cp>\u003Cstrong>OAuth Protected Resource Metadata — \u003Ccode>\u002F.well-known\u002Foauth-protected-resource\u003C\u002Fcode>\u003C\u002Fstrong>\u003Cbr \u002F>\nComplements the OAuth\u002FOIDC feature by publishing RFC 9728 Protected Resource Metadata. Disabled by default.\u003C\u002Fp>\n\u003Cp>\u003Cstrong>robots.txt Content Signals\u003C\u002Fstrong>\u003Cbr \u002F>\nAppends Content Signals directives to your \u003Ccode>robots.txt\u003C\u002Fcode> file, declaring your preferences for how AI systems may use your content:\u003C\u002Fp>\n\u003Cul>\n\u003Cli>\u003Cstrong>ai-train\u003C\u002Fstrong> — whether AI companies may use your content to train models\u003C\u002Fli>\n\u003Cli>\u003Cstrong>search\u003C\u002Fstrong> — whether search engines may index your content\u003C\u002Fli>\n\u003Cli>\u003Cstrong>ai-input\u003C\u002Fstrong> — whether AI retrieval systems (RAG) may use your content as input\u003C\u002Fli>\n\u003C\u002Ful>\n\u003Cp>\u003Cstrong>Markdown Negotiation\u003C\u002Fstrong>\u003Cbr \u002F>\nWhen an AI agent sends a request with the \u003Ccode>Accept: text\u002Fmarkdown\u003C\u002Fcode> header, the plugin intercepts the response for singular posts and pages and returns a clean Markdown version of the content. Regular browser requests are completely unaffected.\u003C\u002Fp>\n\u003Cp>\u003Cstrong>WebMCP\u003C\u002Fstrong>\u003Cbr \u002F>\nInjects a small JavaScript snippet into your page footer that calls \u003Ccode>navigator.modelContext.provideContext()\u003C\u002Fcode>, exposing your site’s key actions as tools to AI agents running in the browser. Built-in tools include blog search, portfolio navigation, and contact page navigation — each individually toggleable.\u003C\u002Fp>\n\u003Cp>\u003Cstrong>llms.txt and llms-full.txt\u003C\u002Fstrong>\u003Cbr \u002F>\nGenerates physical \u003Ccode>\u002Fllms.txt\u003C\u002Fcode> and \u003Ccode>\u002Fllms-full.txt\u003C\u002Fcode> files in your WordPress web root per the \u003Ca href=\"https:\u002F\u002Fllmstxt.org\" rel=\"nofollow ugc\">llmstxt.org\u003C\u002Fa> specification. These files give AI systems a structured, readable index of your site’s content — who you are, what pages exist, and what your posts are about.\u003C\u002Fp>\n\u003Cpre>\u003Ccode>llms.txt contains your site header and a clean list of links by content type. `llms-full.txt` contains the same structure but expands each entry with an excerpt or truncated content block so AI systems can understand the content without fetching every URL.\n\u003C\u002Fcode>\u003C\u002Fpre>\n\u003Cp>Files are regenerated automatically when posts are published, unpublished, or trashed, and whenever settings are saved. A manual Regenerate button is available in the llms.txt settings tab. If your host prevents direct file writes, the generated content is displayed in the admin as a copyable textarea so you can create the files manually.\u003C\u002Fp>\n\u003Cp>Configurable options include a custom intro block, toggling pages and posts independently, selecting additional custom post types, setting the excerpt word limit for \u003Ccode>llms-full.txt\u003C\u002Fcode>, and defining optional additional links that appear under an \u003Ccode>## Optional\u003C\u002Fcode> section in both files.\u003C\u002Fp>\n\u003Ch4>Developer Filters\u003C\u002Fh4>\n\u003Cp>Two filters let themes and other plugins extend the plugin’s output without touching settings:\u003C\u002Fp>\n\u003Cpre>\u003Ccode>kp_agent_skills — add entries to the agent skills index:\n\nadd_filter( 'kp_agent_skills', function ( array $skills ): array {\n    $skills[] = [\n        'name'        => 'my-skill',\n        'type'        => 'api',\n        'description' => 'Does something useful.',\n        'url'         => 'https:\u002F\u002Fyoursite.com\u002Fapi\u002Fendpoint',\n    ];\n    return $skills;\n} );\n\nkp_webmcp_tools — add tools to the WebMCP context:\n\nadd_filter( 'kp_webmcp_tools', function ( array $tools ): array {\n    \u002F\u002F $tools is the PHP array that becomes the JS tools array\n    return $tools;\n} );\n\u003C\u002Fcode>\u003C\u002Fpre>\n","Make your WordPress site discoverable and usable by AI agents via well-known endpoints, MCP, OAuth, and Markdown negotiation.",50,477,100,1,"2026-06-18T14:09:00.000Z","7.1","6.8","8.2",[20,21,22,23,24],"agents","ai","markdown","mcp","well-known","https:\u002F\u002Fgithub.com\u002Fkpirnie\u002Fwppplugin-kp-agent-ready","https:\u002F\u002Fdownloads.wordpress.org\u002Fplugin\u002Fkp-agent-ready.1.1.88.zip",0,null,"2026-07-22T17:31:50.256Z","no_bundle",[],{"slug":33,"display_name":7,"profile_url":8,"plugin_count":34,"total_installs":35,"avg_security_score":13,"avg_patch_time_days":36,"trust_score":37,"computed_at":38},"kevp75",3,1550,30,94,"2026-08-24T00:40:55.032Z",[40,59,77,94,109],{"slug":41,"name":42,"version":43,"author":44,"author_profile":45,"description":46,"short_description":47,"active_installs":48,"downloaded":49,"rating":13,"num_ratings":14,"last_updated":50,"tested_up_to":51,"requires_at_least":52,"requires_php":53,"tags":54,"homepage":57,"download_link":58,"security_score":13,"vuln_count":27,"unpatched_count":27,"last_vuln_date":28,"fetched_at":29},"mescio-for-agents","Mescio for Agents","1.7.0","Mescio","https:\u002F\u002Fprofiles.wordpress.org\u002Fvinsmach\u002F","\u003Cp>\u003Cstrong>Mescio for Agents\u003C\u002Fstrong> makes your WordPress site AI-ready by silently serving posts, pages and WooCommerce products as clean, structured Markdown to any AI agent or LLM pipeline that requests it — using the standard HTTP \u003Ccode>Accept: text\u002Fmarkdown\u003C\u002Fcode> content negotiation header.\u003C\u002Fp>\n\u003Cp>Human visitors using a browser are \u003Cstrong>completely unaffected\u003C\u002Fstrong>. Mescio for Agents only activates when an AI agent or crawler explicitly asks for Markdown.\u003C\u002Fp>\n\u003Ch4>Why Markdown?\u003C\u002Fh4>\n\u003Cp>Feeding raw HTML to an AI is expensive and noisy. A heading like \u003Ccode>## About Us\u003C\u002Fcode> costs ~3 tokens in Markdown vs 12–15 tokens as HTML — before accounting for \u003Ccode>\u003Cdiv>\u003C\u002Fcode> wrappers, navigation bars and script tags that carry zero semantic value. This blog post you are reading takes 16,180 tokens in HTML and 3,150 tokens in Markdown. That is an 80% reduction.\u003C\u002Fp>\n\u003Cp>Markdown has become the \u003Cem>lingua franca\u003C\u002Fem> for AI systems. Mescio for Agents lets your site speak it natively, at zero cost to your human visitors.\u003C\u002Fp>\n\u003Ch4>How it works\u003C\u002Fh4>\n\u003Cp>When an HTTP client sends a request with \u003Ccode>Accept: text\u002Fmarkdown\u003C\u002Fcode>, Mescio for Agents intercepts the WordPress request lifecycle before any template is rendered, converts the post content to clean Markdown, and returns it with the correct \u003Ccode>Content-Type: text\u002Fmarkdown\u003C\u002Fcode> header.\u003C\u002Fp>\n\u003Cpre>\u003Ccode>curl https:\u002F\u002Fyoursite.com\u002Fyour-post\u002F \\\n  -H \"Accept: text\u002Fmarkdown\"\n\u003C\u002Fcode>\u003C\u002Fpre>\n\u003Ch4>Features\u003C\u002Fh4>\n\u003Cul>\n\u003Cli>\u003Cstrong>Zero configuration\u003C\u002Fstrong> — works out of the box on any singular post, page or custom post type\u003C\u002Fli>\n\u003Cli>\u003Cstrong>\u003Ccode>\u002Fllms.txt\u003C\u002Fcode> endpoint\u003C\u002Fstrong> — auto-generated index of all your content in the \u003Ca href=\"https:\u002F\u002Fllmstxt.org\" rel=\"nofollow ugc\">llmstxt.org\u003C\u002Fa> standard format, so AI agents can discover what’s on your site\u003C\u002Fli>\n\u003Cli>\u003Cstrong>\u003Ccode>\u002Fllms-full.txt\u003C\u002Fcode> endpoint\u003C\u002Fstrong> — full site content in a single Markdown file, ready for RAG pipelines\u003C\u002Fli>\n\u003Cli>\u003Cstrong>WooCommerce support\u003C\u002Fstrong> — product pages include price, SKU, stock status, rating, attributes and gallery; products are grouped by category in \u003Ccode>llms.txt\u003C\u002Fcode>\u003C\u002Fli>\n\u003Cli>\u003Cstrong>YAML front matter\u003C\u002Fstrong> — every document includes structured metadata (title, description, URL, date, categories, tags, featured image)\u003C\u002Fli>\n\u003Cli>\u003Cstrong>Multilingual\u003C\u002Fstrong> — detects language via WPML, Polylang, TranslatePress or WordPress locale; emits \u003Ccode>Content-Language\u003C\u002Fcode> and \u003Ccode>Link: rel=alternate\u003C\u002Fcode> headers\u003C\u002Fli>\n\u003Cli>\u003Cstrong>REST API endpoint\u003C\u002Fstrong> — \u003Ccode>\u002Fwp-json\u002Fmescio-for-agents\u002Fv1\u002Fmarkdown?id=\u003Cpost_id>\u003C\u002Fcode> or \u003Ccode>?url=\u003Cpermalink>\u003C\u002Fcode>\u003C\u002Fli>\n\u003Cli>\u003Cstrong>Page builder cleanup\u003C\u002Fstrong> — aggressively strips Elementor, Divi, WPBakery and Beaver Builder layout noise\u003C\u002Fli>\n\u003Cli>\u003Cstrong>Token count header\u003C\u002Fstrong> — \u003Ccode>X-Markdown-Tokens\u003C\u002Fcode> tells AI pipelines how large the document is before processing\u003C\u002Fli>\n\u003Cli>\u003Cstrong>Content Signals\u003C\u002Fstrong> — emits \u003Ccode>Content-Signal: ai-train=yes, search=yes, ai-input=yes\u003C\u002Fcode>\u003C\u002Fli>\n\u003Cli>\u003Cstrong>Correct HTTP caching\u003C\u002Fstrong> — \u003Ccode>Vary: Accept\u003C\u002Fcode> ensures CDNs cache HTML and Markdown versions separately\u003C\u002Fli>\n\u003C\u002Ful>\n\u003Ch4>Response headers\u003C\u002Fh4>\n\u003Cul>\n\u003Cli>\u003Ccode>Content-Type: text\u002Fmarkdown; charset=utf-8\u003C\u002Fcode>\u003C\u002Fli>\n\u003Cli>\u003Ccode>Content-Language: it\u003C\u002Fcode> (or detected language)\u003C\u002Fli>\n\u003Cli>\u003Ccode>Vary: Accept\u003C\u002Fcode>\u003C\u002Fli>\n\u003Cli>\u003Ccode>X-Markdown-Tokens: 725\u003C\u002Fcode>\u003C\u002Fli>\n\u003Cli>\u003Ccode>Content-Signal: ai-train=yes, search=yes, ai-input=yes\u003C\u002Fcode>\u003C\u002Fli>\n\u003Cli>\u003Ccode>Link: \u003Curl>; rel=\"alternate\"; hreflang=\"en\"\u003C\u002Fcode> (when translations available)\u003C\u002Fli>\n\u003C\u002Ful>\n\u003Ch4>Multilingual plugin support\u003C\u002Fh4>\n\u003Cul>\n\u003Cli>\u003Cstrong>WPML\u003C\u002Fstrong> — reads language and available translations automatically\u003C\u002Fli>\n\u003Cli>\u003Cstrong>Polylang\u003C\u002Fstrong> — reads language and links to translated post IDs\u003C\u002Fli>\n\u003Cli>\u003Cstrong>TranslatePress\u003C\u002Fstrong> — reads \u003Ccode>trp_language\u003C\u002Fcode> post meta\u003C\u002Fli>\n\u003Cli>\u003Cstrong>Manual\u003C\u002Fstrong> — configure primary language and additional languages in Settings \u003Cspan aria-hidden=\"true\" class=\"wp-exclude-emoji\">→\u003C\u002Fspan> Mescio for Agents\u003C\u002Fli>\n\u003C\u002Ful>\n\u003Ch4>REST API\u003C\u002Fh4>\n\u003Cpre>\u003Ccode>GET \u002Fwp-json\u002Fmescio-for-agents\u002Fv1\u002Fmarkdown?id=42\nGET \u002Fwp-json\u002Fmescio-for-agents\u002Fv1\u002Fmarkdown?url=https:\u002F\u002Fyoursite.com\u002Fmy-page\u002F\n\u003C\u002Fcode>\u003C\u002Fpre>\n\u003Ch4>Developer hooks\u003C\u002Fh4>\n\u003Cp>\u003Cstrong>Filter: \u003Ccode>mescio_enabled_post_types\u003C\u002Fcode>\u003C\u002Fstrong> — add or remove post types dynamically.\u003C\u002Fp>\n\u003Cp>\u003Cstrong>Filter: \u003Ccode>mescio_pre_convert_content\u003C\u002Fcode>\u003C\u002Fstrong> — modify the HTML before conversion to Markdown.\u003C\u002Fp>\n\u003Cp>\u003Cstrong>Filter: \u003Ccode>mescio_post_convert_content\u003C\u002Fcode>\u003C\u002Fstrong> — modify the Markdown after conversion.\u003C\u002Fp>\n\u003Ch4>Privacy\u003C\u002Fh4>\n\u003Cp>This plugin does not collect, store or transmit any personal data. It does not set cookies. It does not make external HTTP requests.\u003C\u002Fp>\n","Mescio for Agents serves your WordPress content as clean Markdown to AI agents and GPT crawlers. Human visitors never notice a thing.",200,1270,"2026-05-23T08:21:00.000Z","6.9.5","6.0","8.0",[20,21,55,22,56],"llm","rest-api","https:\u002F\u002Fwordpress.org\u002Fplugins\u002Fmescio-for-agents\u002F","https:\u002F\u002Fdownloads.wordpress.org\u002Fplugin\u002Fmescio-for-agents.1.7.0.zip",{"slug":60,"name":61,"version":62,"author":63,"author_profile":64,"description":65,"short_description":66,"active_installs":13,"downloaded":67,"rating":27,"num_ratings":27,"last_updated":68,"tested_up_to":69,"requires_at_least":70,"requires_php":71,"tags":72,"homepage":75,"download_link":76,"security_score":13,"vuln_count":27,"unpatched_count":27,"last_vuln_date":28,"fetched_at":29},"conversion-agent-discovery","Conversion Agent Discovery","0.4.0","agenciaconversion","https:\u002F\u002Fprofiles.wordpress.org\u002Fagenciaconversion\u002F","\u003Cp>Conversion Agent Discovery helps WordPress sites expose public, read-only discovery surfaces for AI agents without pretending to support capabilities that are not implemented.\u003C\u002Fp>\n\u003Cp>It is designed to improve measurable agent accessibility for public, read-only discovery checks without calling external scanners automatically.\u003C\u002Fp>\n\u003Cp>Features include:\u003C\u002Fp>\n\u003Cul>\n\u003Cli>Markdown negotiation for public content with \u003Ccode>Accept: text\u002Fmarkdown\u003C\u002Fcode>.\u003C\u002Fli>\n\u003Cli>Content Signals in \u003Ccode>robots.txt\u003C\u002Fcode>.\u003C\u002Fli>\n\u003Cli>Generated \u003Ccode>llms.txt\u003C\u002Fcode> and \u003Ccode>\u002F.well-known\u002Fllms.txt\u003C\u002Fcode>.\u003C\u002Fli>\n\u003Cli>Editable AI Instructions page for official brand facts and LLM guidance, starting empty with English templates by default.\u003C\u002Fli>\n\u003Cli>Runtime Front-end Placement for exact, design-safe AI Instructions link placement across matching public header, footer, or page content components.\u003C\u002Fli>\n\u003Cli>\u003Ccode>[conversion_ai_instructions_link]\u003C\u002Fcode> shortcode for manual placement.\u003C\u002Fli>\n\u003Cli>Generated \u003Ccode>\u002F.well-known\u002Fapi-catalog\u003C\u002Fcode>.\u003C\u002Fli>\n\u003Cli>Generated \u003Ccode>\u002F.well-known\u002Fagent-skills\u002Findex.json\u003C\u002Fcode> and virtual \u003Ccode>SKILL.md\u003C\u002Fcode> files.\u003C\u002Fli>\n\u003Cli>Local Agent Skills discovery schema generated by the site.\u003C\u002Fli>\n\u003Cli>Read-only WebMCP tool registration with runtime diagnostics for compatible browsers.\u003C\u002Fli>\n\u003Cli>Production-oriented Agentic Browsing readiness guidance for PageSpeed and Lighthouse checks.\u003C\u002Fli>\n\u003Cli>Optional origin isolation headers and optional Origin-Trial header for browser WebMCP runtime support.\u003C\u002Fli>\n\u003Cli>Opt-in declarative WebMCP form annotations for exact rendered form opening tags.\u003C\u002Fli>\n\u003Cli>Public read-only REST endpoints for site search, recent content, single content reads, site context, and contact handoff.\u003C\u002Fli>\n\u003Cli>Agentic Browsing diagnostics that separate plugin-controlled discovery surfaces from theme accessibility and layout stability checks.\u003C\u002Fli>\n\u003Cli>Admin settings page with a global public switch.\u003C\u002Fli>\n\u003C\u002Ful>\n\u003Cp>Conversion Agent Discovery does not publish fake OAuth, MCP Server Card, A2A, or commerce metadata.\u003C\u002Fp>\n\u003Cp>The AI Instructions feature was inspired by Chris Long’s public LinkedIn post and Nectiv case study showing that AI Instructions pages can be cited by ChatGPT in branded queries. It also credits the earlier Seer Interactive AI Information page by Wil Reynolds and Alisa Scharf that Chris Long identified as an important example.\u003C\u002Fp>\n\u003Cp>References:\u003C\u002Fp>\n\u003Cul>\n\u003Cli>Chris Long’s LinkedIn post: https:\u002F\u002Fwww.linkedin.com\u002Fposts\u002Fchris-long-marketing_holy-moly-seos-ai-instruction-pages-influence-share-7466096236799053824-_rpb\u002F\u003C\u002Fli>\n\u003Cli>Nectiv case study: https:\u002F\u002Fnectivdigital.com\u002Fblog\u002Faeo-experiment-chatgpt-cited-an-ai-instructions-page-in-48-hours\u003C\u002Fli>\n\u003Cli>Nectiv AI Instructions example: https:\u002F\u002Fnectivdigital.com\u002Fai-instructions\u003C\u002Fli>\n\u003Cli>Seer Interactive AI Information example: https:\u002F\u002Fwww.seerinteractive.com\u002Fai-information\u003C\u002Fli>\n\u003Cli>Omniscient Digital AI Info example: https:\u002F\u002Fbeomniscient.com\u002Fai-info\u002F\u003C\u002Fli>\n\u003Cli>llms.txt proposal by Jeremy Howard: https:\u002F\u002Fllmstxt.org\u002F\u003C\u002Fli>\n\u003C\u002Ful>\n\u003Cp>Important: this plugin does not guarantee LLM citations, search rankings, AI Overview visibility, or model behavior. It provides controlled public discovery surfaces for experimentation.\u003C\u002Fp>\n\u003Ch3>External Services\u003C\u002Fh3>\n\u003Cp>This plugin does not send requests to external services automatically and does not transmit visitor or site data to third parties.\u003C\u002Fp>\n\u003Cp>The generated Agent Skills discovery document uses a local schema URL served by the WordPress site at \u003Ccode>\u002F.well-known\u002Fagent-skills\u002Fdiscovery-0.2.schema.json\u003C\u002Fcode>; it does not depend on an external schema service.\u003C\u002Fp>\n\u003Cp>The plugin contains optional external links that administrators or users may open manually:\u003C\u002Fp>\n\u003Cul>\n\u003Cli>\u003Ccode>https:\u002F\u002Fconversion.ag\u002F\u003C\u002Fcode> is linked for Conversion attribution and plugin author information. The plugin does not send visitor or site data to Conversion; the link is opened only when a user clicks it manually. Conversion’s privacy policy is available at https:\u002F\u002Fwww.conversion.com.br\u002Fpolitica-de-privacidade\u002F.\u003C\u002Fli>\n\u003Cli>\u003Ccode>https:\u002F\u002Fgithub.com\u002Fagencia-conversion\u002Fconversion-agent-discovery\u003C\u002Fcode> is linked as the public development repository and release source. The plugin does not send visitor or site data to GitHub; the link is opened only when a user clicks it manually. GitHub’s terms are available at https:\u002F\u002Fdocs.github.com\u002Fen\u002Fsite-policy\u002Fgithub-terms\u002Fgithub-terms-of-service and GitHub’s privacy statement is available at https:\u002F\u002Fdocs.github.com\u002Fen\u002Fsite-policy\u002Fprivacy-policies\u002Fgithub-general-privacy-statement.\u003C\u002Fli>\n\u003Cli>\u003Ccode>https:\u002F\u002Fwordpress.org\u002Fplugins\u002Fwp-graphql\u002F\u003C\u002Fcode> is linked from the admin screen when WPGraphQL is not detected, so administrators can optionally install it. The plugin does not send visitor or site data to WordPress.org; the link is opened only when an administrator clicks it manually. WordPress.org’s privacy policy is available at https:\u002F\u002Fwordpress.org\u002Fabout\u002Fprivacy\u002F and terms are available at https:\u002F\u002Fwordpress.org\u002Fabout\u002Fterms-of-service\u002F.\u003C\u002Fli>\n\u003Cli>\u003Ccode>https:\u002F\u002Fpagespeed.web.dev\u002F\u003C\u002Fcode> is linked from the Agentic Browsing admin screen so administrators can manually test their public site in PageSpeed Insights. The plugin does not send visitor or site data to Google automatically; the link is opened only when an administrator clicks it manually. Google’s privacy policy is available at https:\u002F\u002Fpolicies.google.com\u002Fprivacy and terms are available at https:\u002F\u002Fpolicies.google.com\u002Fterms.\u003C\u002Fli>\n\u003C\u002Ful>\n\u003Cp>The developer-only \u003Ccode>tools\u002Frun-agentic-lighthouse.sh\u003C\u002Fcode> script is not run by WordPress and is never executed automatically. If a developer runs it manually, it uses \u003Ccode>npx\u003C\u002Fcode> to download and run Lighthouse from the npm registry and audits only the URL supplied by the developer.\u003C\u002Fp>\n\u003Cp>The optional WebMCP Origin Trial token field is empty by default. If an administrator adds a public Chrome origin trial token, the plugin sends it as an \u003Ccode>Origin-Trial\u003C\u002Fcode> response header on public pages together with the opt-in WebMCP origin isolation headers. The plugin does not request or generate tokens and does not make a server-side request to Google or Chrome services.\u003C\u002Fp>\n\u003Cp>Conversion’s privacy policy is available at https:\u002F\u002Fwww.conversion.com.br\u002Fpolitica-de-privacidade\u002F.\u003C\u002Fp>\n\u003Ch3>Privacy\u003C\u002Fh3>\n\u003Cp>Conversion Agent Discovery does not track users and does not send site data to external services automatically. Outbound links in the admin screen and readme are plain manual links.\u003C\u002Fp>\n\u003Ch3>Development\u003C\u002Fh3>\n\u003Cp>Development happens at https:\u002F\u002Fgithub.com\u002Fagencia-conversion\u002Fconversion-agent-discovery. The distributed plugin contains readable PHP, JavaScript, CSS, and SVG source files; no build step is required to run the plugin.\u003C\u002Fp>\n\u003Cp>Local Agentic Browsing validation can be run by developers with:\u003C\u002Fp>\n\u003Cul>\n\u003Cli>\u003Ccode>tools\u002Fsetup-agentic-fixture.sh\u003C\u002Fcode>\u003C\u002Fli>\n\u003Cli>\u003Ccode>tools\u002Frun-agentic-lighthouse.sh http:\u002F\u002Flocalhost:8089\u002F\u003C\u002Fcode>\u003C\u002Fli>\n\u003Cli>\u003Ccode>node tools\u002Fassert-agentic-lighthouse.mjs .context\u002Flighthouse-agentic.json\u003C\u002Fcode>\u003C\u002Fli>\n\u003Cli>\u003Ccode>CAD_REQUIRE_WEBMCP=1 node tools\u002Fassert-agentic-lighthouse.mjs .context\u002Flighthouse-agentic.json\u003C\u002Fcode> when running a Chrome runtime that exposes real WebMCP APIs.\u003C\u002Fli>\n\u003C\u002Ful>\n\u003Cp>Public 0.4.0 launch materials are available in the repository:\u003C\u002Fp>\n\u003Cul>\n\u003Cli>\u003Ccode>docs\u002Flaunch-0.4.0.md\u003C\u002Fcode>\u003C\u002Fli>\n\u003Cli>\u003Ccode>docs\u002Flocal-agentic-browsing-activation.md\u003C\u002Fcode>\u003C\u002Fli>\n\u003Cli>\u003Ccode>docs\u002Fdemo-checklist-0.4.0.md\u003C\u002Fcode>\u003C\u002Fli>\n\u003Cli>\u003Ccode>docs\u002Fchangelog-0.4.0.md\u003C\u002Fcode>\u003C\u002Fli>\n\u003C\u002Ful>\n","Read-only agent discovery for WordPress: llms.txt, Markdown, API Catalog, Agent Skills, WebMCP, and content signals.",485,"2026-06-17T22:00:00.000Z","7.0.2","5.9","7.4",[20,21,73,74,22],"discovery","llms-txt","https:\u002F\u002Fgithub.com\u002Fagencia-conversion\u002Fconversion-agent-discovery","https:\u002F\u002Fdownloads.wordpress.org\u002Fplugin\u002Fconversion-agent-discovery.0.4.0.zip",{"slug":78,"name":79,"version":80,"author":81,"author_profile":82,"description":83,"short_description":84,"active_installs":85,"downloaded":86,"rating":13,"num_ratings":14,"last_updated":87,"tested_up_to":16,"requires_at_least":52,"requires_php":71,"tags":88,"homepage":92,"download_link":93,"security_score":13,"vuln_count":27,"unpatched_count":27,"last_vuln_date":28,"fetched_at":29},"agentimus","Agentimus – AI SEO, llms.txt & MCP for AI Agents","1.27.1","Sheikh Heera","https:\u002F\u002Fprofiles.wordpress.org\u002Fheera\u002F","\u003Cp>Agentimus is an all-in-one AI SEO plugin for the age of AI agents — AEO (Answer Engine Optimization) and GEO (Generative Engine Optimization) in one place. It does two things.\u003C\u002Fp>\n\u003Cp>\u003Cstrong>It makes your site legible and citable.\u003C\u002Fstrong> It helps AI assistants like ChatGPT, Claude and Perplexity find your site, read it correctly, and cite it in your own words — and shows you which AI bots are actually visiting. \u003Cstrong>You don’t need to understand AI or web standards to use it:\u003C\u002Fstrong> a setup wizard walks you through everything in about a minute on your first visit, then it runs on its own.\u003C\u002Fp>\n\u003Cp>\u003Cstrong>And it lets the AI tools you already use operate your site.\u003C\u002Fstrong> Turn on the built-in Model Context Protocol (MCP) server and the AI tools you use — Claude Code, Claude Desktop, Cursor, Codex — can read your reports and, behind two more opt-in switches, \u003Cstrong>draft, edit and publish posts and pages\u003C\u002Fstrong> for you. Every write runs as the signed-in WordPress user, permission-checked and audited; all three switches are off by default. And when you’d rather stay in wp-admin, a built-in \u003Cstrong>writing assistant\u003C\u002Fstrong> drafts and revises posts for you — no external tool needed. (Full details below.)\u003C\u002Fp>\n\u003Cp>You also get a first-party log of every AI crawler that fetches your content, one-click blocking for bots you don’t want, and a dashboard that scores your agent readiness — one AEO\u002FGEO score across five rungs, with per-page tips and always the next thing to improve.\u003C\u002Fp>\n\u003Cp>By default it makes no outbound requests, collects no analytics, and logs no IP addresses — everything runs on your own site. Optional, off-by-default features change that only when enabled: \u003Cstrong>AI Visibility\u003C\u002Fstrong> queries an AI provider you choose (your own key), \u003Cstrong>Verify bot identities\u003C\u002Fstrong> makes DNS lookups and fetches operators’ published crawler-IP lists, and \u003Cstrong>Store IP addresses\u003C\u002Fstrong> records IPs for flagged crawlers only (see \u003Cem>External services\u003C\u002Fem>).\u003C\u002Fp>\n\u003Cp>\u003Cstrong>📖 Full documentation\u003C\u002Fstrong> — a plain-English user manual and a developer reference, with step-by-step guides for every feature: https:\u002F\u002Fheera.github.io\u002Fagentimus\u002F\u003C\u002Fp>\n\u003Cp>\u003Cstrong>Operate your site from your AI agent (MCP) — opt-in\u003C\u002Fstrong>\u003C\u002Fp>\n\u003Cul>\n\u003Cli>\u003Cstrong>A Model Context Protocol server on your own site\u003C\u002Fstrong> — one switch (Settings \u003Cspan aria-hidden=\"true\" class=\"wp-exclude-emoji\">→\u003C\u002Fspan> Discovery) runs an MCP server at \u003Ccode>\u002Fwp-json\u002Fagentimus\u002Fv1\u002Fmcp\u003C\u002Fcode>; the whole library ships with the plugin, nothing extra to install. The AI tools you already use — \u003Cstrong>Claude Code, Claude Desktop, Cursor, Codex\u003C\u002Fstrong> — connect to it, and the card writes the exact setup for your tool: pick it, mint a key, copy the config, and a Test button proves the connection.\u003C\u002Fli>\n\u003Cli>\u003Cstrong>Read your site’s data\u003C\u002Fstrong> — connected agents can run the read-only tools (readiness\u002FAEO-GEO score, AI traffic, request log, bot identification, and page \u002F JSON-LD \u002F Markdown previews) — the same ones WordPress’s built-in AI gets.\u003C\u002Fli>\n\u003Cli>\u003Cstrong>Draft, edit and publish posts — behind two more switches\u003C\u002Fstrong> — turn on \u003Cstrong>Let connected agents write\u003C\u002Fstrong> and the agent can create and edit posts and pages fully dressed (categories, tags, featured image, AI topics and descriptions) and apply Readiness fixes; turn on a third switch and it may publish, otherwise it leaves drafts for your review.\u003C\u002Fli>\n\u003Cli>\u003Cstrong>Safe by construction\u003C\u002Fstrong> — every write runs as the signed-in WordPress user, never exceeding their permissions, and is recorded under \u003Cstrong>More \u003Cspan aria-hidden=\"true\" class=\"wp-exclude-emoji\">→\u003C\u002Fspan> Agent Access\u003C\u002Fstrong>, attributed to the key. Nothing is public (each call signs in and keeps its screen’s permission check), and with the write switch off the write tools don’t exist on any surface. All three switches are off by default.\u003C\u002Fli>\n\u003C\u002Ful>\n\u003Cp>\u003Cstrong>Write with AI in wp-admin — the built-in assistant (opt-in)\u003C\u002Fstrong>\u003C\u002Fp>\n\u003Cul>\n\u003Cli>\u003Cstrong>Idea \u003Cspan aria-hidden=\"true\" class=\"wp-exclude-emoji\">→\u003C\u002Fspan> draft without leaving wp-admin\u003C\u002Fstrong> — a quill button opens the writing assistant: describe the post, edit the outline it proposes, and preview the complete draft — real editor blocks, AI description, topics, categories, tags. Nothing is saved until you click \u003Cstrong>Create draft\u003C\u002Fstrong>, and it never publishes.\u003C\u002Fli>\n\u003Cli>\u003Cstrong>Edit existing posts\u003C\u002Fstrong> — describe the change and it revises the content; a post’s status never changes, and WordPress revisions keep every prior version.\u003C\u002Fli>\n\u003Cli>\u003Cstrong>Images where you write\u003C\u002Fstrong> — drafts arrive with alt-filled image placeholders; every image block gains \u003Cstrong>Generate image from the alt text\u003C\u002Fstrong>, the sidebar a \u003Cstrong>Featured image (AI)\u003C\u002Fstrong> panel — or pick from your library.\u003C\u002Fli>\n\u003Cli>\u003Cstrong>Ask AI on any block\u003C\u002Fstrong> — rewrite, shorten or extend a paragraph, heading, list or quote with one instruction; normal undo brings anything back. Everything runs on WordPress’s built-in AI Client (7.0+, Settings \u003Cspan aria-hidden=\"true\" class=\"wp-exclude-emoji\">→\u003C\u002Fspan> AI — Agentimus never sees your key), the same connection behind \u003Cstrong>Draft with AI\u003C\u002Fstrong> and \u003Cstrong>Fix with AI\u003C\u002Fstrong>, and every AI button hides until a provider is set up.\u003C\u002Fli>\n\u003C\u002Ful>\n\u003Cp>\u003Cstrong>Control — who may use your content\u003C\u002Fstrong>\u003C\u002Fp>\n\u003Cul>\n\u003Cli>\u003Cstrong>robots.txt content-signals + AI-training blocklist\u003C\u002Fstrong> — declare your content-usage policy and block named model-training crawlers (GPTBot, CCBot, ClaudeBot, Google-Extended, Bytespider, …) by name, while leaving read\u002Fcite bots free.\u003C\u002Fli>\n\u003Cli>\u003Cstrong>Block scanners & scrapers (opt-in hard block)\u003C\u002Fstrong> — robots rules are a polite request; this enforces them, returning 403 to the user-agents on your denylist (and, optionally, agents disguised as ancient handsets — a classic scanner trick). Your \u003Cstrong>always-allowed\u003C\u002Fstrong> list is never blocked: pre-trust well-known AI assistants with one click; major search engines are recognised automatically, and SSL-renewal requests always stay reachable.\u003C\u002Fli>\n\u003C\u002Ful>\n\u003Cp>\u003Cstrong>Reduce exposure — what your site reveals to bots\u003C\u002Fstrong>\u003C\u002Fp>\n\u003Cul>\n\u003Cli>\u003Cstrong>Exposure controls (opt-in, all OFF by default)\u003C\u002Fstrong> — switches that quietly close what stock WordPress reveals to anonymous crawlers: username enumeration, author archives, the WordPress version, the auto-generated \u003Ccode>\u003Chead>\u003C\u002Fcode> discovery links, and XML-RPC. Nothing changes until you turn one on, and signed-in admins and the block editor are never affected. Exposure hygiene, not a firewall.\u003C\u002Fli>\n\u003C\u002Ful>\n\u003Cp>\u003Cstrong>Visibility — who is reading you\u003C\u002Fstrong>\u003C\u002Fp>\n\u003Cul>\n\u003Cli>\u003Cstrong>Agent activity log\u003C\u002Fstrong> — a dashboard of which AI crawlers and agents actually fetch your content and endpoints (GPTBot, Claude, Perplexity, Googlebot, …), recorded first-party in your own database, with no IP logging by default (an optional setting stores IPs for flagged crawlers only).\u003C\u002Fli>\n\u003Cli>\u003Cstrong>Activity to review\u003C\u002Fstrong> — a nav-bar queue surfaces the clients worth a second look — new, unusually high-volume, or spoofing what they are — names a recognised crawler where it can, and offers one-click \u003Cstrong>Block\u003C\u002Fstrong> or \u003Cstrong>Allow\u003C\u002Fstrong> (trust). Nothing is blocked unless you choose to.\u003C\u002Fli>\n\u003Cli>\u003Cstrong>Request Log\u003C\u002Fstrong> — every recorded request, one row each, under \u003Cem>More \u003Cspan aria-hidden=\"true\" class=\"wp-exclude-emoji\">→\u003C\u002Fspan> Request Log\u003C\u002Fem>. Filter by client, endpoint, network, user-agent and date to see exactly what a single bot fetched.\u003C\u002Fli>\n\u003Cli>\u003Cstrong>Agent Access\u003C\u002Fstrong> — the other side of the log: who \u003Cem>authenticates to and acts on\u003C\u002Fem> the machine surface Agentimus creates (\u003Cem>More \u003Cspan aria-hidden=\"true\" class=\"wp-exclude-emoji\">→\u003C\u002Fspan> Agent Access\u003C\u002Fem>): application passwords created, used, renamed or revoked; abilities run; requests refused. A record, not a guard — no IP logging, it names the key used, not the person.\u003C\u002Fli>\n\u003Cli>\u003Cstrong>Traffic from AI\u003C\u002Fstrong> — the mirror of the crawler log: the real visitors an AI assistant sent you, day by day, by assistant and by landing page (\u003Cem>More \u003Cspan aria-hidden=\"true\" class=\"wp-exclude-emoji\">→\u003C\u002Fspan> AI Traffic\u003C\u002Fem>) — daily aggregate counts, never a row for one person, no IP. An opt-in \u003Cstrong>CDN mode\u003C\u002Fstrong> keeps counts accurate behind a full-page cache, and a \u003Cstrong>Find missed AI sources\u003C\u002Fstrong> diagnostic surfaces referrers Agentimus couldn’t name.\u003C\u002Fli>\n\u003Cli>\u003Cstrong>You decide how long it’s kept\u003C\u002Fstrong> — a retention period, nightly auto-delete, and a hard size cap that always applies (Settings \u003Cspan aria-hidden=\"true\" class=\"wp-exclude-emoji\">→\u003C\u002Fspan> Visit log), so the log can never grow without limit on your host.\u003C\u002Fli>\n\u003Cli>\u003Cstrong>AI Visibility (opt-in)\u003C\u002Fstrong> — track \u003Cstrong>each brand, product or person you choose\u003C\u002Fstrong> across ChatGPT, Perplexity, Gemini and Claude. For every one, Agentimus asks the questions your audience actually types and reports whether it gets \u003Cstrong>mentioned, linked, and how it ranks against its rivals\u003C\u002Fstrong> — over time. Tell it what each thing \u003Cem>is\u003C\u002Fem> (\u003Cem>“a WordPress SEO plugin”\u003C\u002Fem>) and it suggests the questions a buyer really types. Off by default; \u003Cstrong>you bring your own API key\u003C\u002Fstrong>, and this is the one feature that makes an outbound request (see \u003Cem>External services\u003C\u002Fem>).\u003C\u002Fli>\n\u003C\u002Ful>\n\u003Cp>\u003Cstrong>Content — clean, machine-readable output\u003C\u002Fstrong>\u003C\u002Fp>\n\u003Cul>\n\u003Cli>\u003Cstrong>Markdown delivery\u003C\u002Fstrong> — request any page as clean markdown by appending \u003Ccode>.md\u003C\u002Fcode> to its URL. (An \u003Ccode>Accept: text\u002Fmarkdown\u003C\u002Fcode> mode for the page’s own URL is also supported, but off by default — one URL with two bodies is unsafe behind a force-caching CDN.)\u003C\u002Fli>\n\u003Cli>\u003Cstrong>\u002Fllms.txt\u003C\u002Fstrong> & \u003Cstrong>\u002Fllms-full.txt\u003C\u002Fstrong> — an \u003Ca href=\"https:\u002F\u002Fllmstxt.org\" rel=\"nofollow ugc\">llmstxt.org\u003C\u002Fa> index of your pages, topics and recent posts, plus a full-text edition an agent can ingest in a single request.\u003C\u002Fli>\n\u003Cli>\u003Cstrong>JSON-LD\u003C\u002Fstrong> — WebSite + Person\u002FOrganization, plus BlogPosting and BreadcrumbList on posts. Automatically \u003Cstrong>defers to Yoast, Rank Math, SEOPress, AIOSEO and The SEO Framework\u003C\u002Fstrong> so you never ship duplicate schema.\u003C\u002Fli>\n\u003Cli>\u003Cstrong>Topics for AI\u003C\u002Fstrong> — say what each post is about in plain words, right in the editor; those topics become the JSON-LD \u003Ccode>keywords\u003C\u002Fcode> and a line in the page’s \u003Ccode>.md\u003C\u002Fcode>, so assistants understand each page’s subject. Type your own, or let Agentimus fill them in from the post’s own tags and categories. Nothing shows on the visible page.\u003C\u002Fli>\n\u003Cli>\u003Cstrong>AI description\u003C\u002Fstrong> — write a one-line summary of each post in the editor; it becomes the JSON-LD \u003Ccode>description\u003C\u002Fcode>, the lead of the page’s \u003Ccode>.md\u003C\u002Fcode>, and the page’s \u003Ccode>\u003Cmeta name=\"description\">\u003C\u002Fcode> (replacing your theme’s, unless an SEO plugin owns it). Blank falls back to the excerpt. A sub-switch can keep it out of your \u003Ccode>\u003Chead>\u003C\u002Fcode>.\u003C\u002Fli>\n\u003Cli>\u003Cstrong>XML sitemap\u003C\u002Fstrong> — an opt-in fallback (index + paginated sub-sitemaps), generated only when neither core nor an SEO plugin provides one, and advertised in robots.txt and llms.txt.\u003C\u002Fli>\n\u003Cli>\u003Cstrong>Change feed\u003C\u002Fstrong> — a JSON feed at \u003Ccode>\u002Fagentimus-changes.json\u003C\u002Fcode> lists your recently added, updated and removed pages, with a \u003Ccode>?since=\u003C\u002Fcode> filter, so an assistant re-checks only what changed instead of re-reading your whole site. On by default and advertised in your discovery document.\u003C\u002Fli>\n\u003C\u002Ful>\n\u003Cp>\u003Cstrong>Identity & contact\u003C\u002Fstrong>\u003C\u002Fp>\n\u003Cul>\n\u003Cli>\u003Cstrong>Author \u002F site identity\u003C\u002Fstrong> — a profile sentence, expertise topics and linked profiles (\u003Ccode>sameAs\u003C\u002Fcode>) feed llms.txt and JSON-LD — the highest-signal lines for agent retrieval.\u003C\u002Fli>\n\u003Cli>\u003Cstrong>security.txt\u003C\u002Fstrong> — optionally publish an RFC 9116 disclosure contact at \u003Ccode>\u002F.well-known\u002Fsecurity.txt\u003C\u002Fcode>.\u003C\u002Fli>\n\u003C\u002Ful>\n\u003Cp>\u003Cstrong>Readiness report\u003C\u002Fstrong>\u003C\u002Fp>\n\u003Cul>\n\u003Cli>A one-screen score of how machine-readable your site is, with a plain-English checklist of what’s enabled and what’s still missing.\u003C\u002Fli>\n\u003Cli>\u003Cstrong>Agent preview\u003C\u002Fstrong> — open it from the Readiness tab to see the exact JSON-LD \u003Cem>and\u003C\u002Fem> Markdown an AI agent receives for the whole site or any page, then copy it. It shows what would ship even when the feature is off or an SEO plugin owns your schema, and a matching read-only preview sits in the post editor — so you never view page source to check what agents read.\u003C\u002Fli>\n\u003Cli>\u003Cstrong>AI Readability tips\u003C\u002Fstrong> — as you write, an “AI Readability” panel flags what makes a page hard for an assistant to read and cite: thin content, missing headings, no opening summary, a nav-heavy page, or images without alt text. It sits in the same “Agentimus” box as the per-page Agent preview, so you check what an agent receives \u003Cem>and\u003C\u002Fem> how readable it is in one place. Editor-only — nothing shows to visitors.\u003C\u002Fli>\n\u003C\u002Ful>\n\u003Cp>\u003Cstrong>Machine discovery (forward-looking)\u003C\u002Fstrong>\u003C\u002Fp>\n\u003Cp>Agentimus also publishes a single, normalized discovery document, built to the conventions the agent ecosystem is converging on (\u003Ccode>.well-known\u003C\u002Fcode>, A2A agent cards, MCP-shaped tools). It puts a site’s identity, capabilities and APIs in one predictable place:\u003C\u002Fp>\n\u003Cul>\n\u003Cli>\u003Cstrong>\u002F.well-known\u002Fdiscovery.json\u003C\u002Fstrong> — an owner-curated document describing the site’s identity, capabilities, APIs and agent cards. Other plugins can declare themselves through a single optional hook, so what an agent needs is aggregated in one place.\u003C\u002Fli>\n\u003Cli>\u003Cstrong>\u002F.well-known\u002Fagent-card.json\u003C\u002Fstrong> and \u003Cstrong>\u002F.well-known\u002Fmcp.json\u003C\u002Fstrong> — an A2A agent card and an MCP manifest, generated automatically.\u003C\u002Fli>\n\u003Cli>\u003Cstrong>Standards-aligned \u003Ccode>.well-known\u003C\u002Fcode> endpoints\u003C\u002Fstrong> — an RFC 9727 \u003Ccode>api-catalog\u003C\u002Fcode>, plus — \u003Cem>only when the capability actually exists\u003C\u002Fem> — an MCP server card and an Agent Skills index. Optional \u003Cstrong>response signing\u003C\u002Fstrong> (Web Bot Auth \u002F HTTP Message Signatures, RFC 9421) signs the discovery documents with an Ed25519 key so agents can verify they came from you; on by default, and the private key stays on your server.\u003C\u002Fli>\n\u003Cli>\u003Cstrong>WordPress Abilities API\u003C\u002Fstrong> — Agentimus registers its own \u003Cstrong>read-only abilities\u003C\u002Fstrong> (readiness\u002FAEO-GEO score, AI traffic, request log, bot checks, and page \u002F JSON-LD \u002F Markdown previews), so WordPress’s built-in AI — and, with the MCP adapter, external agents — can read them, each gated by the same capability as its screen. A separate, off-by-default switch adds the write abilities above.\u003C\u002Fli>\n\u003Cli>\u003Cstrong>Zero-config auto-discovery\u003C\u002Fstrong> — reads your registered REST API namespaces, public post types and the WordPress Abilities API, so a site is described even when no plugin declares itself. A \u003Cstrong>Discovery Hub\u003C\u002Fstrong> admin screen shows what an agent can see, and you decide what is published.\u003C\u002Fli>\n\u003C\u002Ful>\n\u003Cp>\u003Cstrong>What’s read today vs. what it readies you for\u003C\u002Fstrong>\u003C\u002Fp>\n\u003Cp>The content signals above (JSON-LD, robots, llms.txt, markdown) are read by search engines and AI tools \u003Cstrong>today\u003C\u002Fstrong>; the discovery document is \u003Cstrong>forward-looking and standards-aligned\u003C\u002Fstrong>, preparing your site for agents as they adopt these conventions. It’s an open convention with a public reference, and the plugin works fully whether or not anything consumes it.\u003C\u002Fp>\n\u003Cp>\u003Cstrong>Why it’s useful\u003C\u002Fstrong>\u003C\u002Fp>\n\u003Cp>Most tools cover one slice — an llms.txt file, a bot blocker, or structured data. Agentimus brings the whole job together in one lightweight package — and tells you what’s still missing.\u003C\u002Fp>\n\u003Ch3>External services\u003C\u002Fh3>\n\u003Cp>Agentimus makes no outbound requests by default: no remote scripts, fonts or analytics, and the agent-activity log stays in your own database with no IP addresses. (IP storage is optional, off by default — see the FAQ.)\u003C\u002Fp>\n\u003Cp>\u003Cstrong>Two opt-in features go outbound; both are off by default.\u003C\u002Fstrong>\u003C\u002Fp>\n\u003Cp>\u003Cstrong>Verify bot identities\u003C\u002Fstrong> makes DNS lookups and, once a day, downloads the IP-range files bot operators publish to verify their crawlers (Google, Microsoft, DuckDuckGo, Apple, OpenAI, Perplexity — or a URL you add yourself). Only those files are fetched; nothing about your site is sent.\u003C\u002Fp>\n\u003Cp>\u003Cstrong>AI Visibility:\u003C\u002Fstrong> when you enable it and add your own API key for a provider, Agentimus sends the prompts you configured to that provider to check whether it mentions and cites your site — only for the engines you turn on, and only when a check runs. Your keys are stored on your own site and used solely for these calls. The providers, with their terms and privacy policies:\u003C\u002Fp>\n\u003Cul>\n\u003Cli>\u003Cstrong>OpenAI (ChatGPT)\u003C\u002Fstrong> — https:\u002F\u002Fopenai.com\u002Fpolicies\u002Fterms-of-use · https:\u002F\u002Fopenai.com\u002Fpolicies\u002Fprivacy-policy\u003C\u002Fli>\n\u003Cli>\u003Cstrong>Perplexity\u003C\u002Fstrong> — https:\u002F\u002Fwww.perplexity.ai\u002Fhub\u002Flegal\u002Fterms-of-service · https:\u002F\u002Fwww.perplexity.ai\u002Fhub\u002Flegal\u002Fprivacy-policy\u003C\u002Fli>\n\u003Cli>\u003Cstrong>Google (Gemini)\u003C\u002Fstrong> — https:\u002F\u002Fai.google.dev\u002Fgemini-api\u002Fterms · https:\u002F\u002Fpolicies.google.com\u002Fprivacy\u003C\u002Fli>\n\u003Cli>\u003Cstrong>Anthropic (Claude)\u003C\u002Fstrong> — https:\u002F\u002Fwww.anthropic.com\u002Flegal\u002Fconsumer-terms · https:\u002F\u002Fwww.anthropic.com\u002Flegal\u002Fprivacy\u003C\u002Fli>\n\u003C\u002Ful>\n\u003Cp>URL-like strings in the plugin’s output are labels, not requests — the discovery documents’ \u003Ccode>$schema\u003C\u002Fcode> value names the format (never fetched), and the \u003Ccode>example.com\u003C\u002Fcode> URLs in \u003Ccode>examples\u002F\u003C\u002Fcode> are documentation placeholders.\u003C\u002Fp>\n","Make your site agent-ready: AI SEO (AEO\u002FGEO), llms.txt & bot control — be found, read & cited by AI — and write, edit & publish via MCP.",10,1258,"2026-07-22T11:53:00.000Z",[89,90,91,74,23],"agent-readiness","ai-agents","ai-seo","https:\u002F\u002Fgithub.com\u002Fheera\u002Fagentimus","https:\u002F\u002Fdownloads.wordpress.org\u002Fplugin\u002Fagentimus.1.27.1.zip",{"slug":95,"name":96,"version":97,"author":98,"author_profile":99,"description":100,"short_description":101,"active_installs":85,"downloaded":102,"rating":27,"num_ratings":27,"last_updated":103,"tested_up_to":69,"requires_at_least":104,"requires_php":71,"tags":105,"homepage":107,"download_link":108,"security_score":13,"vuln_count":27,"unpatched_count":27,"last_vuln_date":28,"fetched_at":29},"videowhisper-agentic-optimization","Agentic Optimization – SEO for AI Agents","1.1.1","videowhisper","https:\u002F\u002Fprofiles.wordpress.org\u002Fvideowhisper\u002F","\u003Cp>Agentic Optimization helps WordPress sites expose public content to AI agents in a safer, WordPress-native way.\u003C\u002Fp>\n\u003Cp>If SEO helped search engines discover, index, and understand websites, Agentic Optimization does something similar for AI agents, assistants, and LLM-powered tools. It gives public WordPress content clearer discovery files, cleaner read-only endpoints, and structured access paths that are easier for agentic systems to use responsibly.\u003C\u002Fp>\n\u003Cp>Instead of trying to make AI tools scrape full themes, shortcodes, and plugin output blindly, this plugin helps site owners publish a more intentional agent-facing layer for public content.\u003C\u002Fp>\n\u003Cp>Features in the free plugin:\u003C\u002Fp>\n\u003Cul>\n\u003Cli>Root-level \u003Ccode>llms.txt\u003C\u002Fcode>\u003C\u002Fli>\n\u003Cli>Optional root-level \u003Ccode>llms-full.txt\u003C\u002Fcode>\u003C\u002Fli>\n\u003Cli>Optional \u003Ccode>\u002F.well-known\u002Fai.txt\u003C\u002Fcode> and \u003Ccode>\u002Fai.txt\u003C\u002Fcode> guidance for AI-agent discovery\u003C\u002Fli>\n\u003Cli>Root-level \u003Ccode>agent-sitemap.xml\u003C\u002Fcode>\u003C\u002Fli>\n\u003Cli>Optional WordPress \u003Ccode>robots.txt\u003C\u002Fcode> enhancement with discovery hints\u003C\u002Fli>\n\u003Cli>Optional AI-agent user-agent routing from public content pages to the markdown view\u003C\u002Fli>\n\u003Cli>Optional public URL format switcher with \u003Ccode>?vwao_view=markdown\u003C\u002Fcode>, \u003Ccode>json\u003C\u002Fcode>, \u003Ccode>html\u003C\u002Fcode>, or \u003Ccode>clean\u003C\u002Fcode>\u003C\u002Fli>\n\u003Cli>Optional agent sitemap mode that lists public markdown variant URLs such as \u003Ccode>?vwao_agent=1\u003C\u002Fcode>\u003C\u002Fli>\n\u003Cli>Public REST search, content, markdown, comments, categories, tags, and site info endpoints\u003C\u002Fli>\n\u003Cli>Read-only MCP endpoint with search, content, comments, taxonomy, and site info tools\u003C\u002Fli>\n\u003Cli>Hard request caps and transient-based rate limiting\u003C\u002Fli>\n\u003Cli>Privacy-friendly analytics with aggregate counts and hashed IP logs only\u003C\u002Fli>\n\u003Cli>Admin-managed site description and site details for llms.txt context\u003C\u002Fli>\n\u003Cli>SEO-aware content exclusion hooks for common noindex patterns\u003C\u002Fli>\n\u003Cli>Extension points for future add-ons and custom integrations\u003C\u002Fli>\n\u003Cli>Formatter and admin hooks for add-ons that extend post type coverage or editorial agent overrides\u003C\u002Fli>\n\u003C\u002Ful>\n\u003Cp>The plugin is intentionally conservative:\u003C\u002Fp>\n\u003Cul>\n\u003Cli>Read-only only\u003C\u002Fli>\n\u003Cli>Public content only\u003C\u002Fli>\n\u003Cli>No drafts, private content, or pending comments\u003C\u002Fli>\n\u003Cli>Comments exposure disabled by default\u003C\u002Fli>\n\u003Cli>MCP disabled by default\u003C\u002Fli>\n\u003Cli>Analytics disabled by default\u003C\u002Fli>\n\u003C\u002Ful>\n\u003Ch3>External Services\u003C\u002Fh3>\n\u003Cp>This plugin generates agent-optimized discovery files and sitemaps using standard XML formats.\u003C\u002Fp>\n\u003Ch4>Sitemaps.org XML Schema\u003C\u002Fh4>\n\u003Cp>The \u003Ccode>agent-sitemap.xml\u003C\u002Fcode> output uses the standard sitemap XML namespace (\u003Ccode>http:\u002F\u002Fwww.sitemaps.org\u002Fschemas\u002Fsitemap\u002F0.9\u003C\u002Fcode>) and a custom extension URN namespace (\u003Ccode>urn:videowhisper:agentic:1.0\u003C\u002Fcode>). These are identifier strings embedded in locally generated XML documents only. No data is transmitted to external services when the sitemap file is generated or served.\u003C\u002Fp>\n\u003Cul>\n\u003Cli>sitemaps.org protocol reference: https:\u002F\u002Fwww.sitemaps.org\u002Fprotocol.html\u003C\u002Fli>\n\u003C\u002Ful>\n","Adds agent-friendly discovery, markdown, search, and read-only MCP access for public WordPress content, like SEO for AI agents and assistants.",487,"2026-06-21T12:29:00.000Z","6.4",[21,74,22,23,106],"search","https:\u002F\u002Fpromptaur.com\u002Fwordpress\u002Fagentic-optimization\u002F","https:\u002F\u002Fdownloads.wordpress.org\u002Fplugin\u002Fvideowhisper-agentic-optimization.zip",{"slug":110,"name":111,"version":112,"author":113,"author_profile":114,"description":115,"short_description":116,"active_installs":27,"downloaded":117,"rating":27,"num_ratings":27,"last_updated":118,"tested_up_to":51,"requires_at_least":119,"requires_php":71,"tags":120,"homepage":124,"download_link":125,"security_score":13,"vuln_count":27,"unpatched_count":27,"last_vuln_date":28,"fetched_at":29},"activity-log-for-mcp","Activity Log for MCP","1.0.0","Riaan K.","https:\u002F\u002Fprofiles.wordpress.org\u002Friaanknoetze\u002F","\u003Cp>AI agents are starting to talk to WordPress sites directly. Claude Desktop, ChatGPT custom GPTs, and a growing list of MCP clients can connect to your site, browse content, place orders, edit posts, or call any custom tool you expose. The Model Context Protocol (MCP) is the open standard that makes this possible.\u003C\u002Fp>\n\u003Cp>The problem: by default, you can’t see any of it. Requests come in, things change, and there’s no record of what an agent actually did, when it did it, or which user it acted as.\u003C\u002Fp>\n\u003Cp>Activity Log for MCP records every MCP request the moment it hits your site. You see the route, the ability that was called, the user it acted as, the request body, the response, and whether it succeeded. Everything is browsable in a clean React admin page that feels like the rest of WordPress.\u003C\u002Fp>\n\u003Cp>If you’re running an AI integration, debugging a custom MCP server, or just want a paper trail before letting agents touch your data — this is the visibility layer.\u003C\u002Fp>\n\u003Ch4>What you get\u003C\u002Fh4>\n\u003Cp>A real-time log of every MCP request, with filters for date range, ability name, and user. Click any row to inspect the full request and response, copy bodies to your clipboard, or trace a single agent session end-to-end. Sortable columns, configurable per-page counts (10 to 500), and full-text search across request and response bodies. Export to CSV when you need to share findings or feed them into another tool.\u003C\u002Fp>\n\u003Cp>The whole interface is built with \u003Ccode>@wordpress\u002Fcomponents\u003C\u002Fcode> so it inherits the WordPress design language — no jarring custom UI to learn.\u003C\u002Fp>\n\u003Ch4>Built for both halves of the audience\u003C\u002Fh4>\n\u003Cp>If you’re a site owner: install, activate, and click into Tools \u003Cspan aria-hidden=\"true\" class=\"wp-exclude-emoji\">→\u003C\u002Fspan> MCP Logs. There’s no setup screen and no configuration — the plugin starts logging the moment an MCP client makes a request.\u003C\u002Fp>\n\u003Cp>If you’re a developer: there’s a full REST API for every admin feature, authenticated via WordPress Application Passwords or WooCommerce API keys. The plugin is also itself MCP-aware — it registers an MCP server with seven abilities, so an AI agent can introspect its own activity log programmatically. Source ships under \u003Ccode>src\u002F\u003C\u002Fcode> and builds with \u003Ccode>npm run build\u003C\u002Fcode>.\u003C\u002Fp>\n\u003Ch4>Why you’d want this\u003C\u002Fh4>\n\u003Cul>\n\u003Cli>Debug a custom MCP integration without tailing server logs\u003C\u002Fli>\n\u003Cli>Audit AI agent activity on production sites before something goes wrong\u003C\u002Fli>\n\u003Cli>Review per-tool error rates to spot which abilities are flaky\u003C\u002Fli>\n\u003Cli>Trace a single agent session end-to-end when something breaks\u003C\u002Fli>\n\u003Cli>Export logs for compliance reviews or external analysis\u003C\u002Fli>\n\u003Cli>Let an AI agent monitor its own activity through the MCP server\u003C\u002Fli>\n\u003C\u002Ful>\n\u003Ch4>REST API\u003C\u002Fh4>\n\u003Cp>Every admin feature is exposed under \u003Ccode>\u002Fwp-json\u002Factivity-log-for-mcp\u002Fv1\u002F\u003C\u002Fcode>:\u003C\u002Fp>\n\u003Cul>\n\u003Cli>\u003Ccode>GET \u002Frequests\u003C\u002Fcode> — list with filters, sort, and pagination\u003C\u002Fli>\n\u003Cli>\u003Ccode>GET \u002Fstats\u003C\u002Fcode> — totals, success rate, and calls per ability\u003C\u002Fli>\n\u003Cli>\u003Ccode>GET \u002Fsessions\u002F{id}\u003C\u002Fcode> — every request in a session, in order\u003C\u002Fli>\n\u003Cli>\u003Ccode>GET \u002Fsearch\u003C\u002Fcode> — full-text across routes, abilities, and bodies\u003C\u002Fli>\n\u003Cli>\u003Ccode>GET \u002Ferrors\u003C\u002Fcode> — recent failed executions and HTTP errors\u003C\u002Fli>\n\u003Cli>\u003Ccode>GET \u002Ftool-performance\u003C\u002Fcode> — per-ability call count, error rate, and unique users\u003C\u002Fli>\n\u003Cli>\u003Ccode>GET \u002Ffilters\u003C\u002Fcode> — distinct ability names and users for dropdowns\u003C\u002Fli>\n\u003Cli>\u003Ccode>GET \u002Fexport-csv\u003C\u002Fcode> — server-side streamed CSV download\u003C\u002Fli>\n\u003Cli>\u003Ccode>DELETE \u002Frequests\u003C\u002Fcode> — clear all logs\u003C\u002Fli>\n\u003Cli>\u003Ccode>DELETE \u002Fretention\u003C\u002Fcode> — delete logs older than a given date\u003C\u002Fli>\n\u003C\u002Ful>\n\u003Ch4>MCP abilities\u003C\u002Fh4>\n\u003Cp>The plugin registers itself as an MCP server (\u003Ccode>activity-log-for-mcp-server\u003C\u002Fcode>) with seven abilities agents can call directly:\u003C\u002Fp>\n\u003Cul>\n\u003Cli>\u003Ccode>get-activity\u003C\u002Fcode> — paginated log retrieval with filters\u003C\u002Fli>\n\u003Cli>\u003Ccode>get-stats\u003C\u002Fcode> — summary metrics with optional date range\u003C\u002Fli>\n\u003Cli>\u003Ccode>get-activity-by-session\u003C\u002Fcode> — full session trace, with optional body exclusion for lighter payloads\u003C\u002Fli>\n\u003Cli>\u003Ccode>search-activity\u003C\u002Fcode> — full-text search across stored requests and responses\u003C\u002Fli>\n\u003Cli>\u003Ccode>analyze-errors\u003C\u002Fcode> — recent errors with full details\u003C\u002Fli>\n\u003Cli>\u003Ccode>get-tool-performance\u003C\u002Fcode> — per-ability performance metrics\u003C\u002Fli>\n\u003Cli>\u003Ccode>clear-old-logs\u003C\u002Fcode> — date-based retention cleanup\u003C\u002Fli>\n\u003C\u002Ful>\n\u003Ch4>Privacy and data handling\u003C\u002Fh4>\n\u003Cp>All data stays in your WordPress database — nothing is sent anywhere. Logs live in a custom table named \u003Ccode>{prefix}alfmcp_requests\u003C\u002Fcode>. You control retention and can clear everything from the admin UI or via REST. There’s no telemetry, no third-party calls, no external dependencies at runtime.\u003C\u002Fp>\n\u003Ch4>Disclaimer\u003C\u002Fh4>\n\u003Cp>Activity Log for MCP is not affiliated with, endorsed by, or sponsored any AI provider or the Model Context Protocol project. “MCP” and “Model Context Protocol” are referenced solely to describe the open protocol that this plugin observes.\u003C\u002Fp>\n\u003Ch3>Privacy Policy\u003C\u002Fh3>\n\u003Cp>Activity Log for MCP records REST API requests that contain the \u003Ccode>Mcp-Session-Id\u003C\u002Fcode> header. Logged data includes request routes, methods, headers, bodies, response data, user IDs, and timestamps. All data is stored in your WordPress database and is never transmitted to external services.\u003C\u002Fp>\n","See exactly what AI agents do on your WordPress site. A complete activity log for every Model Context Protocol (MCP) request.",219,"2026-05-11T12:41:00.000Z","6.9",[121,90,122,23,123],"activity-log","audit-log","model-context-protocol","","https:\u002F\u002Fdownloads.wordpress.org\u002Fplugin\u002Factivity-log-for-mcp.1.0.0.zip",{"error":127,"url":128,"statusCode":129,"statusMessage":130,"message":130},true,"http:\u002F\u002Flocalhost\u002Fapi\u002Fplugins\u002Fkp-agent-ready\u002Fbundle",404,"no bundle for this plugin yet",{"slug":4,"current_version":6,"total_versions":132,"versions":133},6,[134,140,147,154,161,168],{"version":6,"download_url":26,"svn_tag_url":135,"released_at":28,"has_diff":136,"diff_files_changed":137,"diff_lines":28,"trac_diff_url":138,"vulnerabilities":139,"is_current":127},"https:\u002F\u002Fplugins.svn.wordpress.org\u002Fkp-agent-ready\u002Ftags\u002F1.1.88\u002F",false,[],"https:\u002F\u002Fplugins.trac.wordpress.org\u002Fchangeset?old_path=%2Fkp-agent-ready%2Ftags%2F1.1.59&new_path=%2Fkp-agent-ready%2Ftags%2F1.1.88",[],{"version":141,"download_url":142,"svn_tag_url":143,"released_at":28,"has_diff":136,"diff_files_changed":144,"diff_lines":28,"trac_diff_url":145,"vulnerabilities":146,"is_current":136},"1.1.59","https:\u002F\u002Fdownloads.wordpress.org\u002Fplugin\u002Fkp-agent-ready.1.1.59.zip","https:\u002F\u002Fplugins.svn.wordpress.org\u002Fkp-agent-ready\u002Ftags\u002F1.1.59\u002F",[],"https:\u002F\u002Fplugins.trac.wordpress.org\u002Fchangeset?old_path=%2Fkp-agent-ready%2Ftags%2F1.1.47&new_path=%2Fkp-agent-ready%2Ftags%2F1.1.59",[],{"version":148,"download_url":149,"svn_tag_url":150,"released_at":28,"has_diff":136,"diff_files_changed":151,"diff_lines":28,"trac_diff_url":152,"vulnerabilities":153,"is_current":136},"1.1.47","https:\u002F\u002Fdownloads.wordpress.org\u002Fplugin\u002Fkp-agent-ready.1.1.47.zip","https:\u002F\u002Fplugins.svn.wordpress.org\u002Fkp-agent-ready\u002Ftags\u002F1.1.47\u002F",[],"https:\u002F\u002Fplugins.trac.wordpress.org\u002Fchangeset?old_path=%2Fkp-agent-ready%2Ftags%2F1.1.39&new_path=%2Fkp-agent-ready%2Ftags%2F1.1.47",[],{"version":155,"download_url":156,"svn_tag_url":157,"released_at":28,"has_diff":136,"diff_files_changed":158,"diff_lines":28,"trac_diff_url":159,"vulnerabilities":160,"is_current":136},"1.1.39","https:\u002F\u002Fdownloads.wordpress.org\u002Fplugin\u002Fkp-agent-ready.1.1.39.zip","https:\u002F\u002Fplugins.svn.wordpress.org\u002Fkp-agent-ready\u002Ftags\u002F1.1.39\u002F",[],"https:\u002F\u002Fplugins.trac.wordpress.org\u002Fchangeset?old_path=%2Fkp-agent-ready%2Ftags%2F1.1.37&new_path=%2Fkp-agent-ready%2Ftags%2F1.1.39",[],{"version":162,"download_url":163,"svn_tag_url":164,"released_at":28,"has_diff":136,"diff_files_changed":165,"diff_lines":28,"trac_diff_url":166,"vulnerabilities":167,"is_current":136},"1.1.37","https:\u002F\u002Fdownloads.wordpress.org\u002Fplugin\u002Fkp-agent-ready.1.1.37.zip","https:\u002F\u002Fplugins.svn.wordpress.org\u002Fkp-agent-ready\u002Ftags\u002F1.1.37\u002F",[],"https:\u002F\u002Fplugins.trac.wordpress.org\u002Fchangeset?old_path=%2Fkp-agent-ready%2Ftags%2F1.1.24&new_path=%2Fkp-agent-ready%2Ftags%2F1.1.37",[],{"version":169,"download_url":170,"svn_tag_url":171,"released_at":28,"has_diff":136,"diff_files_changed":172,"diff_lines":28,"trac_diff_url":28,"vulnerabilities":173,"is_current":136},"1.1.24","https:\u002F\u002Fdownloads.wordpress.org\u002Fplugin\u002Fkp-agent-ready.1.1.24.zip","https:\u002F\u002Fplugins.svn.wordpress.org\u002Fkp-agent-ready\u002Ftags\u002F1.1.24\u002F",[],[]]