MCP Server

Kleisli.IO's documentation site exposes a Model Context Protocol (MCP) server so AI agents can search and fetch documentation programmatically. This page describes the server, its tools and resources, and how to connect.

What is MCP?

The Model Context Protocol is a JSON-RPC 2.0 based protocol for exposing tools and resources to LLM clients. The Kleisli docs MCP server speaks the Streamable HTTP transport — POST for client-to-server requests, GET for server-initiated SSE, DELETE for session termination.

Connection

Transport endpoint: https://docs.kleisli.io/mcp/transport
Protocol: Streamable HTTP per spec 2025-03-26
Authentication: none (public read-only surface)

To initialize a session, POST a standard MCP initialize request:

json

{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "initialize",
  "params": {
    "protocolVersion": "2025-03-26",
    "capabilities": {},
    "clientInfo": {"name": "your-client", "version": "1.0.0"}
  }
}

The server responds with an Mcp-Session-Id header that subsequent requests must echo back.

Tools

3 read-only tools. Each links to a detail page with input schema, example JSON-RPC envelope, and applicable error codes.

`get_page`

Get a documentation page as raw Markdown content.

`list_projects`

List all documentation projects with their descriptions.

`search_docs`

Search documentation across all projects. Returns matching pages with titles and relevance scores.

Resources

Documentation pages are also exposed as MCP resources under the docs://kleisli/ URI scheme:

docs://kleisli/{project}/{section}/{page} — individual doc pages
docs://kleisli/llms.txt — global discovery index
docs://kleisli/llms-full.txt — full documentation content
docs://kleisli/{project}/llms.txt — per-project discovery index
docs://kleisli/{project}/llms-full.txt — per-project full content

Use resources/list to enumerate; resources/read to fetch.

Client configuration

Claude Code

Add to ~/.claude/mcp.json (or your project's .mcp.json):

json

{
  "mcpServers": {
    "kleisli-docs": {
      "type": "http",
      "url": "https://docs.kleisli.io/mcp/transport"
    }
  }
}

Cursor

Add to mcp-server-config.json:

json

{
  "mcpServers": {
    "kleisli-docs": {
      "url": "https://docs.kleisli.io/mcp/transport"
    }
  }
}

Generic / curl

bash

curl -X POST https://docs.kleisli.io/mcp/transport \
  -H 'Content-Type: application/json' \
  -H 'Accept: application/json, text/event-stream' \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}'

Discovery surface

The MCP server is one of several AI-discovery affordances on docs.kleisli.io:

/llms.txt — curated Markdown index of all documentation
/llms-full.txt — full content concatenated for token-efficient ingestion
<link rel="alternate" type="text/markdown"> and <meta name="ai-content-discovery"> on every page
Link: </llms.txt>; rel="llms-txt" and X-Llms-Txt: /llms.txt HTTP headers on every response