Agentimus MCP server
Commit Nov 2, 2026Makes WordPress sites AI-ready by providing machine-readable content and an MCP server for AI agents to read and manage site content.
Also known as heera/agentimus
- Stars
- 2
- Tools
- —
- Downloads, 30 days
- —
- Latest version
- 1.33.0
- Last commit
- Nov 2, 2026
- License
- GPL-2.0
What is Agentimus MCP?
Agentimus makes WordPress sites AI-ready by providing machine-readable content and an MCP server for AI agents to read and manage site content.
Summary generated from the project's README
About Agentimus MCP server
Agentimus transforms WordPress websites into machine-readable environments designed for AI agents and search engines. It achieves this by generating specialized endpoints like llms.txt and markdown versions of your pages, alongside structured JSON-LD data. This makes your site content easy for large language models to parse, cite, and understand. The plugin also provides a dashboard to score your site's readiness across categories like findability and readability, offering a ranked list of specific content issues to fix.
Developers and site owners can connect AI tools like Claude Desktop, Claude Code, or Cursor directly to their WordPress installation via a built-in Model Context Protocol server. By using an application password for authentication, these clients can access various tools to read site traffic, check content issues, or manage posts. While read-only access is standard, you can enable write permissions to allow agents to draft, edit, and manage content under your existing user permissions and security constraints.
What you can do with it
- 1Audit AI visibilityAsk an AI client to analyze your site's readiness for AI-driven search and identify specific content gaps.
- 2Automate content draftingInstruct an agent to create new page drafts with appropriate topics and descriptions based on your site's existing taxonomy.
- 3Monitor bot trafficUse an AI assistant to review how many bots are accessing your site and which specific pages they are targeting.
- 4Improve content citabilityRequest a scan of your articles to find passages that are suitable for AI models to quote as authoritative sources.
Written from the project's README. Every use case is checked against a quote from it.
How to install Agentimus MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall Agentimus MCP in Claude Code
$ claude mcp add --transport http agentimus https://heera.it/wp-json/agentimus/v1/mcpInstall Agentimus MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"agentimus": {
"url": "https://heera.it/wp-json/agentimus/v1/mcp"
}
}
}Install Agentimus MCP in VS Code
.vscode/mcp.json
{
"servers": {
"agentimus": {
"type": "http",
"url": "https://heera.it/wp-json/agentimus/v1/mcp"
}
}
}Install Agentimus MCP in VS Code CLI
$ code --add-mcp '{"name":"agentimus","type":"http","url":"https://heera.it/wp-json/agentimus/v1/mcp"}'Install Agentimus MCP in Codex
$ codex mcp add agentimus --url https://heera.it/wp-json/agentimus/v1/mcpInstall Agentimus MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.agentimus] url = "https://heera.it/wp-json/agentimus/v1/mcp"
Install Agentimus MCP in Gemini CLI
$ gemini mcp add -s user --transport http agentimus https://heera.it/wp-json/agentimus/v1/mcpInstall Agentimus MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"agentimus": {
"url": "https://heera.it/wp-json/agentimus/v1/mcp",
"type": "http"
}
}
}Automated checks
Ran Nov 14, 2026Full report →Not verified yet. A server needs a score of 80, no serious finding, and enough data for us to check. How checks work · What to fix for more points
- Source repository linked and reachableheera/agentimus is public and reachablegithub.com/heera/agentimus ↗Pass
- Package names this repository as its sourceNot checked
- Build provenance (Sigstore attestation)Not checked
- Open source license (OSI)GPL-2.0spdx.org/licenses/GPL-2.0.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-11-02github.com/heera/agentimus ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNot checked
- No critical advisory in the package or its dependenciesNot checked
- No hidden instructions to the model0 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNot checked
- Remote endpoint answers the MCP handshakeinitialize answered with protocol 2025-06-18 in 255 msPass
README
View on GitHubAgentimus
Two things for the age of AI agents. (1) Make any WordPress site legible and citable —
llms.txt, a full-text edition, markdown delivery, JSON-LD, content-signal robots rules —
then score how AEO/GEO-ready it is and what to fix next. (2) Let the AI tools you already
use operate the site over MCP: a Model Context Protocol server ships inside the plugin, so
Claude Code, Claude Desktop, Cursor or Codex can read your readiness/traffic/bot data and —
at the level you choose — draft, edit and publish posts and pages, each write running
as the signed-in user, permission-checked and audited. Lightweight, no SEO bloat, no framework.
Live on WordPress.org: https://wordpress.org/plugins/agentimus/
📖 Documentation: https://heera.github.io/agentimus/ — full user manual and developer reference.
Install
- From your dashboard — Plugins → Add New → search "Agentimus" → Install → Activate.
- From WordPress.org — https://wordpress.org/plugins/agentimus/.
- From source — clone this repo, run
npm install && npm run build(producesassets/admin/), then copy or symlink the folder intowp-content/plugins/.
What it does
| Signal | Endpoint / output |
|---|---|
| Link index | /llms.txt |
| Full-text edition | /llms-full.txt |
| Markdown delivery | /<slug>.md; Accept: text/markdown on the page URL is opt-in (agentimus_negotiate_markdown filter, off by default — a CDN caches one answer per URL) |
| Structured data | JSON-LD WebSite + Person/Organization + BlogPosting + BreadcrumbList (defers to SEO plugins) |
| Topics for AI | Per-page topics → JSON-LD keywords + about DefinedTerm entities (with optional Wikidata sameAs via the agentimus_topic_links filter) + a Topics: line in /<slug>.md; static (editor) or derived from tags & categories |
| AI description | Per-page one-line summary → JSON-LD description + the /<slug>.md lead + an authoritative <meta name="description"> (replaces the theme's, defers to an SEO plugin); editor-set, falling back to the excerpt or a ~30-word content summary. A settings sub-toggle can limit it to the JSON-LD + .md surfaces only |
| Writing assistant (opt-in) | The quill button on every Agentimus screen opens a drawer: brief → editable outline → the article writes every section in parallel (/assistant/compose-section per part + one dressing call; long posts aren't capped by a single response, a failed part retries alone, and a mid-write reload resumes) → full preview (title, real blocks, AI description, topics, suggested categories/tags, draft/pending choice) → Create draft lands straight in the editor. Drafts are written to the same bar the Readability panel grades — a liftable opening summary, quotable paragraph lengths, plain sentences, cited sources (readability_rules(), its paragraph cap derived from PageCheck's own threshold). Creation only: a drafted post opens in the editor, where revision lives (the drawer's old edit path and its safe-block gate are gone — that gate existed because a drawer can only handle blocks it wrote itself, and declining real posts was the wrong answer to the right problem). Shapes are per type: Assistant::shape_for() writes a hierarchical type as a PAGE — no invented sections, no image slots, no taxonomy, [placeholder] where only the owner knows a fact — and MCP creation runs the same prompts. Images arrive as alt-filled placeholder blocks: Generate image from the alt text on every image block, a Featured image (AI) sidebar panel, and Ask AI at three scopes — one block, a multi-block selection (BlockSettingsMenuControls, since InspectorControls never renders during multi-select), or a document planner that returns an outline-scoped edit list applied one at a time against a re-read anchor map (replaceBlocks mints new clientIds, so stale ids silently no-op). Server-side it's the same audited write path as MCP (Assistant.php → ContentWriter), gated by enable_agent_writes + the user's own caps, with every generation routed through Assist::generate() (rate-limited, Content-Guidelines-aware) and status clamped to draft|pending — the assistant can never publish |
| Write with AI (opt-in) | Editor "Draft with AI" writes the AI description and "Suggest with AI" fills Topics, both from the page's own content; "Fix with AI" drafts a fix per AI-Readability warning (opening summary inserts in one click, the rest copy-only). Routes through the WordPress 7.0 AI Client — your own provider key, never handled by the plugin; hidden until a provider is configured under Settings → Connectors |
| AI abilities | Two tiers via wp_register_ability, each ability permission-gated like its source screen. Read (always registered): agentimus/read-readiness, read-findings (the Findings screen's own ranked front door, bounded at 12 rows), read-audience (people and machines counted apart, never summed), read-ai-visibility, read-ai-traffic, read-request-log, read-edge-traffic, read-search-visibility, read-search-performance, read-search-opportunities, read-google-index (optional url answers from stored checks, no quota), identify-bot, read-content-issues (which pages need work, what each is flagged for, and how old that verdict is — the list read-findings summarises), read-terms (the categories and tags this site already uses, by the exact names the write tools expect), check-page, preview-schema/-markdown, scan-exposed-files, suggest-internal-links, read-settings, check-focus, read-citation-products, suggest-citation-questions, search-media (title + _wp_attachment_image_alt, gated on upload_files). Write (registered only while enable_agent_writes is on — off by default, requires the MCP server switch, and off means the abilities don't exist on any surface): create-content/update-content (draft-first; categories & tags by name with wp-admin's own creation rules, featured image by attachment ID or sideloaded URL, AI description/topics in the same call), write-description, write-topics, write-search-fields (the focus keyword and the SEO title — the two fields that decide how a page appears in a search result, and the last two an agent could not reach), and apply-fix (enacts a readiness check's own remediation from a closed vocabulary that can only enable documented features). update-settings and save-citation-product need agent_writes_settings, refresh-data and purge-edge-cache need agent_writes_maintenance, and list-content, create-term, update-term, import-media, update-media, trash-content and restore-content need agent_writes_content, all off by default. Scheduling with publish_at needs agent_writes_content and agent_writes_publish. Writes refuse markup that can run in a browser, under any login. status=publish needs agent_writes_publish (the "Publish without your review" extra) plus the user's own publish cap. The MCP card shows these switches as one choice, Off, Read or Write, plus extras (resources/admin/js/agentLevel.js) |
| MCP server (opt-in) | /wp-json/agentimus/v1/mcp — the WordPress MCP Adapter ships inside the plugin (Composer-vendored, Jetpack-autoloader arbitrated) behind the enable_mcp_server switch (Settings → Discovery, off by default; WP 6.9+). External MCP clients (Claude Code, Claude Desktop, Codex) authenticate with an application password and get exactly the abilities above — the read-only tools, plus the write tools only at the Write level (enable_agent_writes), and four resources (llms.txt, llms-full.txt, discovery.json, the agent card) declared with meta.mcp.uri; a resource whose endpoint is switched off is never registered (the server's self-description says which tier it's running) — the adapter's generic execute-any-ability default server stays suppressed, every call is audited in Agent Access, and toggling off hard-disconnects live clients. At the Off level, the library is never loaded and no endpoint exists |
| XML sitemap | /agentimus-sitemap.xml — opt-in fallback, generated only when neither WordPress core nor an SEO plugin already provides one (sitemap index + paginated sub-sitemaps) |
| Crawler policy | robots.txt content-signal + training-crawler blocklist |
| Discovery layer | /.well-known/discovery.json (+ agent-card.json, mcp.json) |
| Change feed | /agentimus-changes.json?since= — recently added, updated and removed content as JSON, so an agent fetches only the delta (advertised in discovery.json; on by default) |
| Crawl enforcement (opt-in) | hard-block (403) denylisted, spoofed-"scanner", or proven-impostor user-agents at the generated endpoints — ACME-safe, off by default; optional bot-identity verification (forward-confirmed reverse DNS + operators' published IP ranges, via an owner-editable Verified-bots registry) so a spoofed bot name can't earn the allowlist and a proven fake is refused |
In the admin
- Findings — one front door for everything open across the site, in the nav with its own count. A single ranked list — pages losing a click they already earn, plus anything the setup checks caught — ordered by what each one costs, every row carrying the button that lands on the fix. The count measures only work you can act on; anything merely waiting on a later report gets a quiet dot instead. Below it, the per-item content worklist: one row per published thing, what it's found for, whether it answers that, and what else it needs.
- Light / dark theme — a toggle showing the mode you're switching to. Dark is a hand-tuned palette, not an inversion, with its own dialect per WordPress admin colour scheme (Default keys neutral, Coffee keys brown and gold). A manual pick holds until the operating system next flips, then the device's rhythm wins again; the resolved mode rides on
<html data-ar-theme>and is remembered per browser, never in Settings. - AEO/GEO score — one 0–100 score on the dashboard across five rungs (Findable / Readable / Trusted / Optimized / Mentioned), with the single most useful next step; each rung deep-links to where you act on it. Mentioned is opt-in (see Citations) and its weight redistributes across the others when off. A score of 99.6 reads 99 — 100 is earned, never rounded into.
- Work by issue — pick one check and every page it flags opens in Your Content, ranked and paged, rather than a sample of six. Fix what a filtered list was opened for and the row keeps its place, marked done, instead of vanishing before you can see the fix land.
- Reading that does not depend on WP-Cron — the content sweep is scheduled work, and on many hosts WordPress's scheduled jobs never run (a cached page never runs PHP, so the request that would start them never arrives). Agentimus notices when its own jobs are overdue and runs them from the admin screen you are already on, joining core's own lock so it can never double-run a job. A site whose cron works loads nothing extra.
- Optimize your content — per-page citability checks (thin content, something concrete to quote, quotable passages, freshness) over your articles, with a worklist of which pages to improve and a matching read-only panel in the editor. Commerce products, commerce plugins' designated pages (cart/checkout/account — WooCommerce options and FluentCart settings both read), and shortcode/block container pages with no authored prose are excluded; set aside any page not meant to be cited (it stays published, just leaves the score) — set-aside is a ledger, so everything you park stays listed and counted rather than merely absent; mark categories evergreen to exempt timeless content from the freshness check.
- Content types, and your veto over them (Settings) — the types a plugin switched on are grouped apart from your own, and you can turn one off even when the plugin that added it wants it on. The writing assistant follows the same rule: a page gets no invented sections, no image slots and no tags, because a page is not an article.
- Screens re-read when you return to them — leaving a data screen and coming back used to show the numbers from whenever the plugin was first opened. Each one now refreshes on return, so what's on screen is what's true.
- Discovery Hub (Discovery tab) — the inventory of everything this site publishes for machines: the providers describing it, the capabilities they declare, the public APIs, the well-known documents, and the MCP & tools surface. The tools section states three separate things in three panels — what a signed-in agent can run (grouped by provider, each group opening to its tool names), the addresses those agents connect to, and what an anonymous agent is handed in
/.well-known/mcp.json. Capability lists scroll inside a fixed height, since their length is the site's to decide (one per public REST post type and taxonomy). Any registration problem is listed with a plain-English fix. - Readiness report — pass/warn/fail checks, each with a plain-English suggestion and a deep link to the fix (including a "sitemap advertised in robots.txt" check).
- Agent preview — a modal (from Readiness) showing the exact JSON-LD and Markdown an agent receives for the site or any page/post, with a grouped site/page/post picker, copy, and validator links. It renders what would ship even when schema is disabled or an SEO plugin owns it; password-protected posts stay hidden, and an unpublished draft is shown as a preview of what it will emit once published. A read-only twin also sits in the post editor.
- Visibility → Search — what people searched, how often you appeared, how often those results were clicked, and the pages that earned them, every number reported by the engine itself. Connect both Google and Bing and a switch appears: the two count different searchers and are never merged. Directly beneath it, Search Opportunities turns those same numbers into a worklist — pages sitting just off page one, and pages on page one being scrolled past — each entry wired to the exact field that fixes it. It also names the searches several of your pages are splitting between them — the clicks divide, so each ranks lower than one page would — with the page that earns the click stated, and one decision on every other. (It lived at the bottom of Readiness until 1.36; Readiness now keeps a pointer to it.)
- Visibility → In the index — whether the engines' indexes actually hold your pages, Bing's and Google's on one screen. Bing is the index ChatGPT search and Copilot read today: how much of your site it holds, how cleanly its crawler gets in, a daily human-traffic series with a week-on-week trend, and a live per-page question answered by Bing's own API. Google's side walks the whole site in rotation and re-checks daily — healthy pages stay a count, anything needing a look earns a row in Google's own words with a deep link into Search Console, and any single URL can be re-inspected on the spot.
- Data sources (Settings → Data sources) — outside services Agentimus reads from, all optional, each with one key held on your own server and no third-party proxy: Cloudflare for what the edge answered or blocked before your server saw it (and, with optional extra token permissions, clearing its cache when you publish and blocking clients you block from the queue), Google Search Console for search and index coverage — with Analytics riding that same key if you want visitor numbers — and Bing Webmaster Tools, which can also announce every change you publish through IndexNow. Numbers land in your own database, so your history outlives each service's own reporting window.
- Citations (Visibility → Citations; opt-in, bring-your-own-key — adds the Mentioned rung to your score, and a reading expires after 90 days so a stale one never counts) — track each brand, product or person you choose across ChatGPT, Perplexity, Gemini and Claude. For every one it asks the questions your audience types and reports whether it's mentioned, linked, and how it ranks against its own rivals, over time. Give an item a category ("WordPress SEO plugin") and Agentimus suggests the questions someone actually types — or, where an AI provider is configured in WordPress, asks that AI for a spread of unbranded questions (
POST /visibility/suggestand/visibility/suggest-ai). Each item has its own website, category, competitors, questions and scoreboard; pause any single one or the whole schedule, and every setting on the screen saves itself. Results are stored locally; it's the only feature that makes outbound calls — using API keys you provide (stored encrypted at rest), off by default. It keeps its own keys rather than reusing WordPress's shared AI connectors, because a visibility check is graded on the sources an engine cited and the shared client drops them. - Agent activity log — a local-only dashboard (no IP logged by default; an optional setting stores IPs for flagged crawlers only) of which AI agents and crawlers fetch your endpoints and pages; repeat hits are grouped with a count, newest first. Click any day's bar for that day's full report — clients, endpoints, and every request. Your own logged-in visits are skipped, and so are the readiness screen's own Verify-live/exposure-scan fetches (they carry a short-lived
X-Agentimus-Selfchecktoken, since they're deliberately anonymous). - Request Log (More → Request Log) — the raw log behind that dashboard: one row per request, keyset-paged, filterable by client, endpoint, network, user-agent and date range. The filters AND together, giving the agent × endpoint cross-tab the summary rollups structurally cannot show.
- Agent Access (More → Agent Access) — the other side of the log: who authenticates to and acts on the machine surface Agentimus creates. Records application passwords being created/first-used/renamed/revoked, WordPress abilities being run, and requests that were refused or probed for abilities that don't exist — and every row says who: the user and the named application password behind it, resolved live (a renamed key shows its current label, a revoked one reads "since revoked"). A record, not a guard (it never blocks); no IP logged, so it names the credential, not the person. Rides
rest_request_after_callbacksand the app-password hooks; the credential half needs no Abilities API, the ability half auto-detects it. - Traffic from AI — a private, first-party count of which AI assistants send visitors to you (per-day tallies of assistant → landing page; no IP, no per-visitor data). The dashboard shows a summary — click any day's bar for that day's assistant → landing-page report; More → Visitors is the full report, with the same per-day drill-down. Every card there says these are people, not agents: the request log is the machine side, Visitors is the human side, and the two are never added together. An opt-in CDN mode counts these in the browser so the numbers survive a full-page cache. Because recognition is a finite list, an opt-in Find missed AI sources diagnostic records the referrer hosts and
utm_sourcetags it couldn't attribute — the only way to see a blind spot that otherwise leaves no trace. - Visit-log retention (Settings → Visit log) — a retention period, nightly auto-delete, and a hard row cap. The cap outranks the retention: "keep for 90 days" is a ceiling on age, not a promise a row survives 90 days. Turning auto-delete off does not mean "keep forever" — the cap still collects, oldest first.
- Keep AI endpoints out of your cache (Settings → Caching & CDN, opt-in) — if a cache or CDN in front of your site serves stored copies of the AI endpoints (
llms.txt, the.well-knowndocs, the change feed), those agent fetches never reach WordPress: the log under-counts them and the change feed can go stale. Turn this on and the endpoints sendCache-Control: no-store, so any cache that respects it lets each fetch through. The readiness report links to it when it detects a cache in front of you. - Refresh AI files when content changes (Settings → Caching & CDN, on by default) — on every content change, asks each detected page cache (WP Rocket, Nginx Helper, W3 Total Cache, LiteSpeed, WP Super Cache, Cache Enabler, or any
agentimus_purge_urllistener) to drop the AI files —llms.txt,llms-full.txt,robots.txt, the change feed, the.well-knowndocs — plus the edited post's own.mdtwin, which a cache plugin otherwise never knows to refresh. Feature-detected, so it's a no-op with no cache present. - Activity to review — a nav-bar review queue flags new, unusually high-volume, spoofed/scanner, or impersonating clients (one that claims a bot from the editable Verified-bots registry — Googlebot, GPTBot, PerplexityBot, … — but conclusively fails that operator's published check: reverse DNS or its published IP ranges), each with a plain "Check this bot" panel and one-click Block / Allow / Ignore. Pairs with the opt-in Block scanners & scrapers enforcement; an optional Store IP addresses for flagged clients setting shows the exact address to block. Every standing decision — blocked, trusted, ignored — is managed later under Settings → AI access → Manage clients: identity, decision date, and one-click undo per row.
- Exposure — opt-in controls that limit what anonymous crawlers can read (username enumeration, author archives, the WP version,
<head>links, XML-RPC), plus a one-click exposed-files scan that checks whether risky files (backups,.env,debug.log, keys) are publicly downloadable and tells you how to block them. Guidance, not a firewall. - Factory reset — one click restores every setting to its recommended defaults, with a preview of exactly what will change.
Architecture
- PHP (
inc/, namespaceAgentimus\, PSR-4 autoloaded) — vanilla, no framework.Pluginorchestrates;Settingsis the single option store;Cachehandles transients;Endpoints/Markdown/Schemaproduce output;Readinessruns the checks;Restbacks the admin;Adminmounts the UI.
- Admin UI — Vue 3 (Options API), built with Vite into
assets/admin/. Talks to the REST namespaceagentimus/v1with the standard WP nonce.
Extending to any site / content type
The free core covers post + page and any public post type you opt in
(Content types card, or the agentimus_post_types filter), so products and
CPTs flow into llms.txt, the full-text edition, markdown and schema automatically.
Deeper coverage (a WooCommerce Product mapper, page-builder content) is an
add-on that hooks these seams:
agentimus_post_types— add/remove agent-visible post typesagentimus_schema_for_post— return a full node, e.g.Productwith offersagentimus_markdown_source— supply rendered HTML for page-builder content
Agentimus MCP questions
How do I add Agentimus MCP to Claude Code?
Run claude mcp add --transport http agentimus https://heera.it/wp-json/agentimus/v1/mcp in your terminal. Add --scope user to make it available in every project.
How do I add Agentimus MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
Is the MCP server enabled by default?
No, the MCP server is opt-in and must be enabled via the Settings → Discovery menu.