About agentverse
agentverse is a hosted MCP server for agentverse documentation, generated with doc2mcp. It lets AI clients retrieve, search, and ask questions about crawled documentation with citations.
Key features
- 01List crawled documentation pages
- 02Retrieve a page as Markdown
- 03Search documentation by headings
- 04Get an overview and index
- 05Read all documentation together
- 06Ask questions with cited answers
Use cases
- 01Find a specific page in agentverse docs
- 02Retrieve Markdown for a documentation page
- 03Search docs while working in an AI client
- 04Ask documentation questions with citations
MCP support
Exposes documentation listing, retrieval, search, overview, full-read, and cited Q&A tools to MCP clients through a hosted endpoint.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://doc2mcp.site/api/mcp/353ba712-2c3b-4699-9c58-0dc4e54ff4eb/mcpclaude mcp add --transport http doc2mcp-agentverse https://doc2mcp.site/api/mcp/353ba712-2c3b-4699-9c58-0dc4e54ff4eb/mcp{"mcpServers":{"doc2mcp-agentverse":{"type":"http","url":"https://doc2mcp.site/api/mcp/353ba712-2c3b-4699-9c58-0dc4e54ff4eb/mcp"}}}Open in Cursor{"servers":{"doc2mcp-agentverse":{"type":"http","url":"https://doc2mcp.site/api/mcp/353ba712-2c3b-4699-9c58-0dc4e54ff4eb/mcp"}}}Open in VS Code{"mcpServers":{"doc2mcp-agentverse":{"type":"http","url":"https://doc2mcp.site/api/mcp/353ba712-2c3b-4699-9c58-0dc4e54ff4eb/mcp"}}}{"mcpServers":{"doc2mcp-agentverse":{"serverUrl":"https://doc2mcp.site/api/mcp/353ba712-2c3b-4699-9c58-0dc4e54ff4eb/mcp"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
https://doc2mcp.site/api/mcp/353ba712-2c3b-4699-9c58-0dc4e54ff4eb/mcpAuth requiredTools
Details
From the project READMEdoc2mcp
Documentation infrastructure for AI agents
Paste any docs URL → get a hosted, Cursor-ready MCP server in under 60 seconds.
Live · Docs · SDK · Marketplace · Open Source
⭐ Star this repo — it helps developers discover doc2mcp on GitHub and the MCP Registry.
Three ways to use doc2mcp

| Surface | Best for | Start here |
|---|---|---|
| Web | Instant convert in the browser | doc2mcp.site |
| CLI | Terminal + one-shot install into Cursor | npm i -g doc2mcp |
| SDK | Code, CI, LangChain / LangGraph / agents | doc2mcp-sdk |
API keys always come from doc2mcp.site (User PAT + project token). The SDK has no separate login.
The pipeline

Docs URL → crawl → analyze → MCP tools → hosted endpoint → Cursor / Claude / LangChain / LangGraph.
1) Web (normal)
- Sign in at doc2mcp.site/login
- Paste a docs URL (Stripe, LangChain, Mintlify, GitHub…)
- Copy the hosted MCP URL + Bearer token into Cursor / Claude / VS Code
{
"mcpServers": {
"my-docs": {
"url": "https://doc2mcp.site/api/mcp/{project_id}/mcp",
"headers": { "Authorization": "Bearer <project-token>" }
}
}
}
2) CLI
npm install -g doc2mcp
doc2mcp login # creates User PAT (d2mcp_pat_…)
doc2mcp https://docs.example.com
Lists the same projects as the dashboard. Install helpers for Cursor / VS Code / Claude / Windsurf.
3) SDK (doc2mcp-sdk)

npm i doc2mcp-sdk
import { Doc2MCP } from "doc2mcp-sdk";
// User PAT from doc2mcp.site / `npx doc2mcp login` — SDK has no auth of its own
const client = new Doc2MCP({ token: process.env.DOC2MCP_API_TOKEN! }); // Settings → d2mcp_usr_…
const ready = await client.convertAndWait({
sourceUrl: "https://js.langchain.com/docs",
});
const answer = await client.callToolText({
mcpUrl: ready.mcp.url,
mcpToken: ready.mcp.token, // project token d2mcp_…
name: "search_documentation",
arguments: { query: "how do runnables work?" },
});
Full handbook (API keys, Cursor, Claude, LangChain, LangGraph, LangSmith, OpenAI, Vercel AI SDK, CrewAI, AutoGen, Mastra):
Product docs page: doc2mcp.site/docs/sdk
MCP tools generated per project
| Tool | What it does |
|---|---|
list_documentation_pages | Every crawled page |
get_documentation_page | Full markdown of one page |
search_documentation | Heading-aware search |
get_documentation_overview | Summary + index |
read_full_documentation | All pages combined |
ask_documentation | Q&A with citations |
Repos
| Repo | Purpose |
|---|---|
| doc2mcp/doc2mcp (this) | Next.js app, CLI, pipeline, MCP runtime |
| doc2mcp/doc2mcp-sdk | Programmatic JS/TS SDK + framework examples |
| doc2mcp/doc2mcp-registry | MCP Registry gateway manifest |
Contribute
- Read CONTRIBUTING.md and CODE_OF_CONDUCT.md
- Branch from
staging→ open PR →staging - AI review (
Gemini PR review) fails the check on must-fix — fix blockers before merge - Coupon
opensourcedoc2mcp→ Starter free for 12 months on Pricing
More: doc2mcp.site/open-source
Local development
pnpm install
cp .env.example .env.local
pnpm dev
pnpm check
pnpm exec tsc --noEmit --skipLibCheck
CI / CD
Feature → staging (preview) → main → v* tag deploys production on Vercel.
PR checks: Biome/Ultracite, TypeScript, Next build, CLI build, Gemini AI review (must-fix → failed check).
License
MIT — see LICENSE.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.