io.github.AshutoshRaj97/agentready-mcp

Official7 toolsLive

by AshutoshRaj97 · JavaScript

Query any docs site via MCP. Submit a URL, ask questions, get cited answers.

agentready-mcp (io.github.AshutoshRaj97/agentready-mcp)

This MCP server enables agents to query documents from a specified website. You submit a URL, and AgentReady crawls the site, generates a spec-compliant llms.txt, and hosts a live /ask RAG endpoint exposed via an MCP server. Responses are returned as cited answers.

🛠️ Key Features

Submit a URL to target any docs site
Crawls the site and generates a spec-compliant llms.txt
Provides a live /ask RAG endpoint via MCP
Returns cited answers

🚀 Use Cases

Ask questions against content from a given docs website
Retrieve cited information from crawled documentation

⚡ Developer Benefits

MCP-compatible access to a docs site’s content
Uses llms.txt and a RAG /ask endpoint for question answering
Supports any MCP-compatible agent client

⚠️ Limitations

Requires providing a URL to crawl and query; scope is the target site only
Capability depends on the hosted AgentReady layer described in the excerpt

Captured live from the server via tools/list.

list_sites

List all websites currently indexed in AgentReady. Use this to check if a domain is already available before submitting it — indexed sites return instant cited answers via ask_site. The index covers developer tools, APIs, cloud platforms, frameworks, databases, and more, and grows as new sites are submitted.

Parameters

No parameters.

Raw schema

{
  "type": "object",
  "properties": {},
  "required": []
}

get_site_capabilities

Return the AgentReady capability manifest for a website. If the site is not indexed yet, AgentReady indexes it automatically before returning its freshness, read-only limits, schemas, and available MCP and HTTP endpoints.

Parameters1

domain

string

required

Domain of the indexed site (e.g. "docs.example.com"). Accepts full URLs too.

Raw schema

{
  "type": "object",
  "properties": {
    "domain": {
      "type": "string",
      "maxLength": 253,
      "description": "Domain of the indexed site (e.g. \"docs.example.com\"). Accepts full URLs too."
    }
  },
  "required": [
    "domain"
  ]
}

plan_site_action

Turn a natural-language request into a grounded, read-only AgentReady plan for a website. If the site is not indexed yet, AgentReady indexes it automatically first. This prototype never executes side effects; it identifies supported steps, sources, risks, and whether a future execution would require confirmation.

Parameters2

domain	string	required	Domain of the indexed site (e.g. "docs.example.com"). Accepts full URLs too.
request	string	required	Natural-language request to plan against the site.

Raw schema

{
  "type": "object",
  "properties": {
    "domain": {
      "type": "string",
      "maxLength": 253,
      "description": "Domain of the indexed site (e.g. \"docs.example.com\"). Accepts full URLs too."
    },
    "request": {
      "type": "string",
      "maxLength": 1000,
      "description": "Natural-language request to plan against the site."
    }
  },
  "required": [
    "domain",
    "request"
  ]
}

submit_site

Index any website so it can be queried with ask_site. Use this when the site is not yet in list_sites. Handles JS-rendered pages (React, Next.js, Vue SPAs) that web_fetch cannot read — uses a four-layer pipeline: llms.txt → HTTP+cheerio → __NEXT_DATA__ extraction → Jina Reader headless browser. Takes ~60 seconds. Once indexed, ask_site queries are instant.

Parameters1

url

string

required

Full URL of the site to index (e.g. "https://docs.example.com").

Raw schema

{
  "type": "object",
  "properties": {
    "url": {
      "type": "string",
      "maxLength": 2048,
      "description": "Full URL of the site to index (e.g. \"https://docs.example.com\")."
    }
  },
  "required": [
    "url"
  ]
}

ask_site

Query any website's documentation and get cited, multi-page answers in natural language. Use ask_site when you need: (1) answers that synthesize information across multiple pages of a site, (2) documentation from JS-rendered sites (React, Next.js, Vue SPAs) where web_fetch returns empty or partial HTML, (3) citations linking back to the exact source pages, (4) faster results than fetching and reading individual pages one by one. For sites not yet indexed, ask_site auto-crawls and answers in ~60s — no separate submit_site call needed.

Parameters3

domain	string	required	Domain of the site to query (e.g. "stripe.com"). Accepts full URLs too.
query	string	required	The question to ask about the site.
url	string	optional	Optional: a specific page URL to focus on. AgentReady will ensure this page is indexed before answering.

Raw schema

{
  "type": "object",
  "properties": {
    "domain": {
      "type": "string",
      "maxLength": 253,
      "description": "Domain of the site to query (e.g. \"stripe.com\"). Accepts full URLs too."
    },
    "query": {
      "type": "string",
      "maxLength": 2000,
      "description": "The question to ask about the site."
    },
    "url": {
      "type": "string",
      "maxLength": 2048,
      "description": "Optional: a specific page URL to focus on. AgentReady will ensure this page is indexed before answering."
    }
  },
  "required": [
    "domain",
    "query"
  ]
}

refresh_site

Force a full re-crawl of a site to pick up new or changed content. If the site has never been indexed, AgentReady performs the initial indexing automatically. Use when ask_site returns outdated information or when you know the site has recently been updated. Takes ~60 seconds. After completion, ask_site returns fresh content.

Parameters1

domain

string

required

Domain of the site to refresh (e.g. "docs.example.com").

Raw schema

{
  "type": "object",
  "properties": {
    "domain": {
      "type": "string",
      "description": "Domain of the site to refresh (e.g. \"docs.example.com\")."
    }
  },
  "required": [
    "domain"
  ]
}

rate_answer

Rate the quality of a previous ask_site answer from 1 (not useful) to 5 (excellent). Pass the request_id returned in structuredContent when available so the rating can be tied to the exact answer.

Parameters4

domain	string	required	Domain that was queried.
rating	integer	required	Answer quality from 1 to 5.
request_id	string	optional	request_id returned by ask_site, when available.
comment	string	optional	Optional short explanation.

Raw schema

{
  "type": "object",
  "properties": {
    "domain": {
      "type": "string",
      "maxLength": 253,
      "description": "Domain that was queried."
    },
    "rating": {
      "type": "integer",
      "minimum": 1,
      "maximum": 5,
      "description": "Answer quality from 1 to 5."
    },
    "request_id": {
      "type": "string",
      "maxLength": 64,
      "description": "request_id returned by ask_site, when available."
    },
    "comment": {
      "type": "string",
      "maxLength": 1000,
      "description": "Optional short explanation."
    }
  },
  "required": [
    "domain",
    "rating"
  ]
}

README.md10 KBView on GitHub

@agentreadyweb/mcp

smithery badge

What is AgentReady?

AgentReady is a hosted capability layer that makes any website discoverable and usable by agents through MCP.

Paste 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.

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.

What's already indexed: Browse the live AgentReady directory → or index any public site yourself.

Key properties:

Works on any public URL — static sites, React/Next.js SPAs, Docusaurus, GitBook, custom engines
No account required to index your first site
Shared index — one team member submits a site, everyone on the team can query it instantly
Handles JS-rendered pages that web_fetch returns empty for
Capability manifests expose freshness, schemas, endpoints, and read-only limits
Grounded plans return evidence, risks, confirmation requirements, and durable receipts

CLI

The same package doubles as a CLI — no install, no account:

bash

# Agent-readiness report card (llms.txt, sitemap, robots, JS-rendering, index status)
npx @agentreadyweb/mcp grade yourdocs.com

# Ask any site a question, get a cited answer (auto-indexes new sites in ~60s)
npx @agentreadyweb/mcp ask stripe.com "what is the test card number?"

# Index or re-crawl a site
npx @agentreadyweb/mcp index yourdocs.com
npx @agentreadyweb/mcp refresh yourdocs.com

For CI, dashboards, or scripts, add --json to receive the raw report on stdout (progress remains on stderr):

bash

npx @agentreadyweb/mcp grade yourdocs.com --json | jq '.grade, .score'

The command still exits 1 when the grade is below B.

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:

yaml

# GitHub Actions — after your docs deploy step
- run: npx @agentreadyweb/mcp refresh yourdocs.com

Connect any MCP-compatible client to AgentReady:

Local MCP bridge (stdio)

For clients that use an mcpServers configuration, add the AgentReady bridge:

json

{
  "mcpServers": {
    "agentready": {
      "command": "npx",
      "args": ["-y", "@agentreadyweb/mcp"]
    }
  }
}

Restart your client. You'll have eight tools available:

list_sites — see all indexed websites
get_site_capabilities — index on demand, then inspect a site manifest, freshness, schemas, and endpoints
get_site_facts — key structured facts extracted from a site
ask_site — query any site with cited, multi-page answers
plan_site_action — index on demand, then create a grounded, read-only plan and receipt
submit_site — index any website so it can be queried
refresh_site — re-crawl a site, or perform its initial index when it is new
rate_answer — submit quality feedback

Cursor

Add to ~/.cursor/mcp.json:

json

{
  "agentready": {
    "command": "npx",
    "args": ["-y", "@agentreadyweb/mcp"]
  }
}

Project or terminal setup

bash

npx @agentreadyweb/mcp

Or add the same agentready server to your client's project configuration to share it with your team:

json

{
  "mcpServers": {
    "agentready": {
      "command": "npx",
      "args": ["-y", "@agentreadyweb/mcp"]
    }
  }
}

VS Code (GitHub Copilot agent mode)

Requires VS Code 1.99+ with the GitHub Copilot extension. Create .vscode/mcp.json in your project root:

json

{
  "servers": {
    "agentready": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "@agentreadyweb/mcp"]
    }
  }
}

Copilot's MCP tools are only available in agent mode. Commit this file to share with your team.

Windsurf / Zed / other clients

Any MCP client that supports stdio transport works the same way — use npx -y @agentreadyweb/mcp as the command.

WebMCP (no install)

If your client supports HTTP transport, connect directly by URL — no npm required:

code

https://www.agentready.it.com/api/mcp

Docusaurus plugin

If your docs site uses Docusaurus, auto-index on every build:

bash

npm install @agentreadyweb/docusaurus-plugin

// docusaurus.config.js
plugins: [
  ['@agentreadyweb/docusaurus-plugin', { domain: 'docs.yoursite.com' }]
]

MkDocs plugin

If your docs site uses MkDocs, auto-index on every build:

bash

pip install mkdocs-agentready

yaml

# mkdocs.yml
plugins:
  - search
  - agentready

If site_url is not set, specify the domain explicitly:

yaml

plugins:
  - agentready:
      domain: docs.yoursite.com

Starlight plugin

If your docs site uses Starlight (Astro), auto-index on every build:

bash

npm install starlight-agentready

// astro.config.mjs
import agentready from 'starlight-agentready'

export default defineConfig({
  site: 'https://docs.yoursite.com',
  integrations: [
    starlight({
      plugins: [agentready()],
    }),
  ],
})

Sphinx extension

If your docs site uses Sphinx, auto-index on every build:

bash

pip install sphinx-agentready

python

# conf.py
extensions = [
    "sphinx_agentready.extension",
]

# Domain is inferred from html_baseurl automatically, or set explicitly:
agentready_domain = "docs.yoursite.com"

Available tools

list_sites

Lists 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.

get_site_capabilities

code

get_site_capabilities(domain: string)

Returns the site's capability manifest, freshness state, schemas, and available HTTP/MCP endpoints.

get_site_facts

code

get_site_facts(domain: string)

Returns key structured facts extracted from a site — pricing tiers, feature lists, limits, and other high-signal data points that agents frequently need.

plan_site_action

code

plan_site_action(domain: string, request: string)

Creates a grounded, read-only plan with evidence, risks, confirmation requirements, and a durable receipt. It does not execute side effects.

submit_site

code

submit_site(url: string)

Index 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.

Example: submit_site("https://docs.example.com")

ask_site

code

ask_site(domain: string, query: string, url?: string)

Ask 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).

Example: ask_site("stripe.com", "What are the fees for card payments?")

refresh_site

code

refresh_site(domain: string)

Force 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.

Example: refresh_site("docs.example.com")

rate_answer

code

rate_answer(domain: string, rating: number, request_id?: string, comment?: string)

Submits 1–5 quality feedback, optionally tied to the exact ask_site request.

Deploy webhook

Automatically re-index your docs on every deploy. No auth required — rate limited to once per hour per domain.

bash

curl -X POST https://www.agentready.it.com/api/webhook/refresh \
  -H "Content-Type: application/json" \
  -d '{"domain": "docs.yoursite.com"}'

Or pass the domain as a query param (works with Vercel/Netlify form-encoded webhook payloads):

code

https://www.agentready.it.com/api/webhook/refresh?domain=docs.yoursite.com

How indexing works

AgentReady uses a layered approach to handle any public website:

llms.txt / llms-full.txt — if the site publishes one, it's used as a high-quality structured content source
Standard HTML crawl — fetches up to 10 pages via sitemap or link crawling, extracts clean text
__NEXT_DATA__ extraction — for Next.js apps, parses server-side rendered data embedded in the HTML
Jina Reader fallback — for JS-only SPAs that return empty HTML, uses a remote rendering service to extract content

Sites behind authentication or with no public HTML content cannot be indexed.

Environment variables

Variable	Default	Description
`AGENTREADY_MCP_URL`	`https://www.agentready.it.com/api/mcp`	Override the MCP endpoint (for self-hosted)
`AGENTREADY_TELEMETRY`	`1`	Set to `0` to disable anonymous usage telemetry

Telemetry

This 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.

Install

Tools (7)

list_sitesget_site_capabilitiesplan_site_actionsubmit_siteask_siterefresh_siterate_answer

Configuration

Environment variables

AGENTREADY_MCP_URL

Override the MCP endpoint URL (only needed for self-hosted AgentReady instances)

Add to VS Code Add to Cursor

claude_desktop_config.json

json

{
  "mcpServers": {
    "agentready-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@agentreadyweb/mcp@1.3.1"
      ],
      "env": {
        "AGENTREADY_MCP_URL": "<YOUR_AGENTREADY_MCP_URL>"
      }
    }
  }
}

agentready-mcp (io.github.AshutoshRaj97/agentready-mcp)

🛠️ Key Features

🚀 Use Cases

⚡ Developer Benefits

⚠️ Limitations

list_sites

get_site_capabilities

plan_site_action

submit_site

ask_site

refresh_site

rate_answer

@agentreadyweb/mcp

What is AgentReady?

CLI

Local MCP bridge (stdio)

Cursor

Project or terminal setup

VS Code (GitHub Copilot agent mode)

Windsurf / Zed / other clients

WebMCP (no install)

Docusaurus plugin

MkDocs plugin

Starlight plugin

Sphinx extension

Available tools

list_sites

get_site_capabilities

get_site_facts

plan_site_action

submit_site

ask_site

refresh_site

rate_answer

Deploy webhook

How indexing works

Environment variables

Telemetry

Install

Configuration

Related servers