{
  "markdown": "# @agentreadyweb/mcp\n\n[![smithery badge](https://smithery.ai/badge/ashudps2004/agentready)](https://smithery.ai/servers/ashudps2004/agentready)\n[![npm](https://img.shields.io/npm/v/@agentreadyweb/mcp)](https://www.npmjs.com/package/@agentreadyweb/mcp)\n\n## What is AgentReady?\n\n[AgentReady](https://www.agentready.it.com) is a hosted capability layer that makes any website discoverable and usable by agents through MCP.\n\nPaste a URL → AgentReady crawls the site, generates a spec-compliant `llms.txt`, and hosts a live `/ask` RAG endpoint and MCP server. Any MCP-compatible agent client can then discover the site, ask natural-language questions, inspect capabilities, and create grounded read-only plans with citations.\n\n**The problem it solves:** AI agents using `web_fetch` fetch one page at a time, get empty HTML from JavaScript SPAs (React, Next.js, Vue), and hallucinate when the answer spans multiple pages. AgentReady indexes the whole site, handles JS rendering, and retrieves across pages — so agents get the right answer instead of a confident wrong one.\n\n**What's already indexed:** Browse the live [AgentReady directory →](https://www.agentready.it.com/directory) or index any public site yourself.\n\n**Key properties:**\n- Works on any public URL — static sites, React/Next.js SPAs, Docusaurus, GitBook, custom engines\n- No account required to index your first site\n- Shared index — one team member submits a site, everyone on the team can query it instantly\n- Handles JS-rendered pages that `web_fetch` returns empty for\n- Capability manifests expose freshness, schemas, endpoints, and read-only limits\n- Grounded plans return evidence, risks, confirmation requirements, and durable receipts\n\n## CLI\n\nThe same package doubles as a CLI — no install, no account:\n\n```bash\n# Agent-readiness report card (llms.txt, sitemap, robots, JS-rendering, index status)\nnpx @agentreadyweb/mcp grade yourdocs.com\n\n# Ask any site a question, get a cited answer (auto-indexes new sites in ~60s)\nnpx @agentreadyweb/mcp ask stripe.com \"what is the test card number?\"\n\n# Index or re-crawl a site\nnpx @agentreadyweb/mcp index yourdocs.com\nnpx @agentreadyweb/mcp refresh yourdocs.com\n```\n\nFor CI, dashboards, or scripts, add `--json` to receive the raw report on\nstdout (progress remains on stderr):\n\n```bash\nnpx @agentreadyweb/mcp grade yourdocs.com --json | jq '.grade, .score'\n```\n\nThe command still exits `1` when the grade is below `B`.\n\n`grade` exits non-zero below a B, so you can use it as a CI gate. `refresh` in your docs deploy pipeline keeps the index fresh automatically:\n\n```yaml\n# GitHub Actions — after your docs deploy step\n- run: npx @agentreadyweb/mcp refresh yourdocs.com\n```\n\n---\n\nConnect any MCP-compatible client to AgentReady:\n\n## Local MCP bridge (stdio)\n\nFor clients that use an `mcpServers` configuration, add the AgentReady bridge:\n\n```json\n{\n  \"mcpServers\": {\n    \"agentready\": {\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"@agentreadyweb/mcp\"]\n    }\n  }\n}\n```\n\nRestart your client. You'll have eight tools available:\n- `list_sites` — see all indexed websites\n- `get_site_capabilities` — index on demand, then inspect a site manifest, freshness, schemas, and endpoints\n- `get_site_facts` — key structured facts extracted from a site\n- `ask_site` — query any site with cited, multi-page answers\n- `plan_site_action` — index on demand, then create a grounded, read-only plan and receipt\n- `submit_site` — index any website so it can be queried\n- `refresh_site` — re-crawl a site, or perform its initial index when it is new\n- `rate_answer` — submit quality feedback\n\n## Cursor\n\nAdd to `~/.cursor/mcp.json`:\n\n```json\n{\n  \"agentready\": {\n    \"command\": \"npx\",\n    \"args\": [\"-y\", \"@agentreadyweb/mcp\"]\n  }\n}\n```\n\n## Project or terminal setup\n\n```bash\nnpx @agentreadyweb/mcp\n```\n\nOr add the same `agentready` server to your client's project configuration to share it with your team:\n\n```json\n{\n  \"mcpServers\": {\n    \"agentready\": {\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"@agentreadyweb/mcp\"]\n    }\n  }\n}\n```\n\n## VS Code (GitHub Copilot agent mode)\n\nRequires VS Code 1.99+ with the GitHub Copilot extension. Create `.vscode/mcp.json` in your project root:\n\n```json\n{\n  \"servers\": {\n    \"agentready\": {\n      \"type\": \"stdio\",\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"@agentreadyweb/mcp\"]\n    }\n  }\n}\n```\n\nCopilot's MCP tools are only available in agent mode. Commit this file to share with your team.\n\n## Windsurf / Zed / other clients\n\nAny MCP client that supports stdio transport works the same way — use `npx -y @agentreadyweb/mcp` as the command.\n\n## WebMCP (no install)\n\nIf your client supports HTTP transport, connect directly by URL — no npm required:\n\n```\nhttps://www.agentready.it.com/api/mcp\n```\n\n## Docusaurus plugin\n\nIf your docs site uses Docusaurus, auto-index on every build:\n\n```bash\nnpm install @agentreadyweb/docusaurus-plugin\n```\n\n```js\n// docusaurus.config.js\nplugins: [\n  ['@agentreadyweb/docusaurus-plugin', { domain: 'docs.yoursite.com' }]\n]\n```\n\n## MkDocs plugin\n\nIf your docs site uses MkDocs, auto-index on every build:\n\n```bash\npip install mkdocs-agentready\n```\n\n```yaml\n# mkdocs.yml\nplugins:\n  - search\n  - agentready\n```\n\nIf `site_url` is not set, specify the domain explicitly:\n\n```yaml\nplugins:\n  - agentready:\n      domain: docs.yoursite.com\n```\n\n## Starlight plugin\n\nIf your docs site uses Starlight (Astro), auto-index on every build:\n\n```bash\nnpm install starlight-agentready\n```\n\n```js\n// astro.config.mjs\nimport agentready from 'starlight-agentready'\n\nexport default defineConfig({\n  site: 'https://docs.yoursite.com',\n  integrations: [\n    starlight({\n      plugins: [agentready()],\n    }),\n  ],\n})\n```\n\n## Sphinx extension\n\nIf your docs site uses Sphinx, auto-index on every build:\n\n```bash\npip install sphinx-agentready\n```\n\n```python\n# conf.py\nextensions = [\n    \"sphinx_agentready.extension\",\n]\n\n# Domain is inferred from html_baseurl automatically, or set explicitly:\nagentready_domain = \"docs.yoursite.com\"\n```\n\n## Available tools\n\n### list_sites\n\nLists all websites currently indexed by AgentReady with their titles and page counts. Use this to check if a domain is already available before submitting it.\n\n### get_site_capabilities\n```\nget_site_capabilities(domain: string)\n```\nReturns the site's capability manifest, freshness state, schemas, and available HTTP/MCP endpoints.\n\n### get_site_facts\n```\nget_site_facts(domain: string)\n```\nReturns key structured facts extracted from a site — pricing tiers, feature lists, limits, and other high-signal data points that agents frequently need.\n\n### plan_site_action\n```\nplan_site_action(domain: string, request: string)\n```\nCreates a grounded, read-only plan with evidence, risks, confirmation requirements, and a durable receipt. It does not execute side effects.\n\n### submit_site\n```\nsubmit_site(url: string)\n```\nIndex any website with AgentReady. Takes ~60 seconds. Handles static sites, server-rendered pages, and JavaScript-heavy SPAs via a four-layer pipeline. Once done, query it with `ask_site`.\n\n**Example:** `submit_site(\"https://docs.example.com\")`\n\n### ask_site\n```\nask_site(domain: string, query: string, url?: string)\n```\nAsk a question about any website and get a cited answer grounded in its content. Synthesises information across multiple pages. If the site isn't indexed yet, AgentReady crawls and indexes it automatically before answering (~60s).\n\n**Example:** `ask_site(\"stripe.com\", \"What are the fees for card payments?\")`\n\n### refresh_site\n```\nrefresh_site(domain: string)\n```\nForce a full re-crawl of a site to pick up new or changed content. If the site is new, AgentReady performs its initial index automatically. Takes ~60 seconds.\n\n**Example:** `refresh_site(\"docs.example.com\")`\n\n### rate_answer\n```\nrate_answer(domain: string, rating: number, request_id?: string, comment?: string)\n```\nSubmits 1–5 quality feedback, optionally tied to the exact `ask_site` request.\n\n## Deploy webhook\n\nAutomatically re-index your docs on every deploy. No auth required — rate limited to once per hour per domain.\n\n```bash\ncurl -X POST https://www.agentready.it.com/api/webhook/refresh \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\"domain\": \"docs.yoursite.com\"}'\n```\n\nOr pass the domain as a query param (works with Vercel/Netlify form-encoded webhook payloads):\n\n```\nhttps://www.agentready.it.com/api/webhook/refresh?domain=docs.yoursite.com\n```\n\n## How indexing works\n\nAgentReady uses a layered approach to handle any public website:\n\n1. **llms.txt / llms-full.txt** — if the site publishes one, it's used as a high-quality structured content source\n2. **Standard HTML crawl** — fetches up to 10 pages via sitemap or link crawling, extracts clean text\n3. **`__NEXT_DATA__` extraction** — for Next.js apps, parses server-side rendered data embedded in the HTML\n4. **Jina Reader fallback** — for JS-only SPAs that return empty HTML, uses a remote rendering service to extract content\n\nSites behind authentication or with no public HTML content cannot be indexed.\n\n## Environment variables\n\n| Variable | Default | Description |\n|----------|---------|-------------|\n| `AGENTREADY_MCP_URL` | `https://www.agentready.it.com/api/mcp` | Override the MCP endpoint (for self-hosted) |\n| `AGENTREADY_TELEMETRY` | `1` | Set to `0` to disable anonymous usage telemetry |\n\n## Telemetry\n\nThis package sends a lightweight anonymous ping to `agentready.it.com/api/telemetry` each time the MCP bridge starts or a CLI command runs. It contains: a random install ID (stored in `~/.agentready/install-id`), package version, Node version, platform, and which mode/command was used. No query content, no domain names, no personal data. Set `AGENTREADY_TELEMETRY=0` to opt out.\n",
  "bytes": 9693,
  "sha": "84d9e7b58aa99c4fc64a561c9c277f991a1bf1a7ac2d97cadb278d4e08dceeca",
  "repo_slug": "ashutoshraj97/agentready-mcp",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_ashutoshraj97_agentready_mcp_545fb374/readme"
}