How do I use OpenClaw Docs MCP?

1. Click on "Install Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@OpenClaw Docs MCP search for deployment guide" That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

OpenClaw Docs MCP

by miguelcc06

Overview Schema Related Servers Score Discussions

Python

Hybrid

📖 OpenClaw Docs MCP

An MCP RAG server providing powerful hybrid search over OpenClaw documentation

OpenClaw Docs MCP indexes the OpenClaw documentation into PostgreSQL using pgvector and exposes powerful hybrid search tools via HTTP using FastMCP.

✨ Key Features

🧠 Hybrid Search: Combines semantic (pgvector) and full-text search across ~721 English documentation pages.
🛠️ 13 MCP Tools: Fully equipped with search, get_chunk, navigation (next/prev), page outlines, and index statistics.
⚡ HTTP Transport: Exposed securely over HTTP with API key authentication.
🔄 Incremental Sync: Smart content-hash syncing to avoid redundant updates.
⚙️ Production Ready: Includes systemd service files and an optional daily sync timer.

Related MCP server: Semantic Search MCP Server

📋 Requirements

Python: 3.11+
Database: PostgreSQL 15+ with the pgvector extension.
AI: OpenAI API key (for embedding generation using text-embedding-3-small).

🚀 Setup & Installation

1. Environment Setup

python3 -m venv .venv
source .venv/bin/activate
pip install -e ".[dev]"

2. Configuration

cp config.env.example config.env
# Edit config.env with: DATABASE_URL, OPENAI_API_KEY, API_KEY

3. Database & Ingestion

# Run migrations (ensure your database exists)
alembic upgrade head

# Crawl sitemap and index content (~5-15 min)
openclaw-docs-mcp ingest --full

4. Run the Server

openclaw-docs-mcp serve

📍 Server runs at http://0.0.0.0:8000/mcp (configurable via MCP_PORT).

🧰 MCP Tools Available

⚠️ Note: Write all queries in English for the best results (docs are indexed in English only).

Tool	Description
`search`	Hybrid semantic + full-text search
`search_in_page`	Search within a single document
`lexical_search`	Full-text search only
`get_chunk`	Full chunk by ID
`get_chunks`	Batch retrieve chunks
`get_chunk_next` / `get_chunk_prev`	Navigate document order
`get_chunk_neighbors`	Previous + current + next
`get_context_window`	Symmetric context around a chunk
`get_document_chunks`	Paginate chunks in a document
`list_pages`	List indexed pages
`get_page_outline`	Headings + chunk IDs
`get_stats`	Index statistics

🔌 Cursor Configuration

🏠 Localhost (same machine)

{
  "mcpServers": {
    "openclaw-docs": {
      "url": "http://127.0.0.1:8000/mcp",
      "headers": {
        "Authorization": "***"
      }
    }
  }
}

🌍 Remote (e.g., Cloudflare tunnel)

{
  "mcpServers": {
    "openclaw-docs": {
      "command": "npx",
      "args": [
        "-y", "mcp-remote@latest",
        "https://your-tunnel.example.com/mcp",
        "--header", "Authorization: Bearer ${OPENCLAW_DOCS_API_KEY}"
      ],
      "env": {
        "OPENCLAW_DOCS_API_KEY": "YOUR_API_KEY"
      }
    }
  }
}

⚙️ systemd Deployment

For automated management and background syncing:

sudo cp deploy/openclaw-docs-mcp.service /etc/systemd/system/
sudo cp deploy/openclaw-docs-mcp-sync.service deploy/openclaw-docs-mcp-sync.timer /etc/systemd/system/
sudo cp deploy/sync-wrapper.sh /home/miguelcc06/openclaw-docs-mcp/deploy/
chmod +x deploy/sync-wrapper.sh

sudo systemctl daemon-reload
sudo systemctl enable --now openclaw-docs-mcp
sudo systemctl enable --now openclaw-docs-mcp-sync.timer

💡 Tip: Set SYNC_ENABLED=true and SYNC_SCHEDULE=daily in config.env.

💻 CLI Commands Quick Reference

openclaw-docs-mcp serve          # Start HTTP MCP server
openclaw-docs-mcp ingest --full  # Full re-index
openclaw-docs-mcp sync           # Incremental sync
openclaw-docs-mcp stats          # Index statistics
alembic upgrade head             # Apply DB migrations

This server cannot be installed

license - permissive license

quality - not tested

maintenance

How are these scores calculated?

Maintenance

–Maintainers

–Response time

–Release cycle

–Releases (12mo)

Commit activity

Resources

GitHub Repository

Need Help?

Related Servers

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Servers

Hybrid RAG Project MCP Server
RAG Systems Vector Databases Search
gwyer
A
license
-
quality
D
maintenance
Enables Claude to perform hybrid search across local documents by combining semantic vector retrieval and BM25 keyword matching for optimal context recovery. It supports multiple file formats including PDF, CSV, and Markdown, leveraging local Ollama models for private and efficient document querying.
Updated 8 months ago (2025-12-14 02:08 UTC)
4
MIT
Semantic Search MCP Server
RAG Systems Code Analysis Search
camilojourney
F
license
-
quality
B
maintenance
Provides hybrid semantic and keyword code search for Claude Code using BM25 and vector retrieval. It enables indexing and searching local codebases with language-aware chunking and local embeddings.
Updated 5 days ago (2026-08-14 21:00 UTC)
knowledge-server
RAG Systems Search Documentation Access
bwarzecha
A
license
-
quality
D
maintenance
Enables LLMs to search and retrieve information from large technical documentation (OpenAPI specs, markdown) via intelligent chunking and semantic search.
Updated a year ago (2025-08-05 22:25 UTC)
MIT
Clarion Knowledge Base
RAG Systems Knowledge & Memory Documentation Access
peterparker57
F
license
-
quality
C
maintenance
Enables semantic search across Clarion programming documentation via natural language queries in Claude AI, supporting 21 manuals and 21,747 indexed chunks.
Updated 10 months ago (2025-10-15 02:13 UTC)

View all related MCP servers

Related MCP Connectors

Ragora
Search your knowledge bases from any AI assistant using hybrid RAG.
ref-tools-mcp
Token-efficient search for coding agents over public and private documentation.
embedded-docs
Page-cited retrieval for embedded docs, datasheets, MISRA, CMSIS, and RTOS references.

View all MCP Connectors

Latest Blog Posts

Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)
By Om-Shree-0709 on July 25, 2026.
mcp
Agent Identity
OAuth 2.1
Your AI Chatbot Just Exposed Your CEO's Salary to an Intern
By Om-Shree-0709 on July 2, 2026.
Agent Identity
MCP Security
OAuth Delegation
Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)
By Om-Shree-0709 on June 30, 2026.
Agentic Ai
Prompt Injection
WebAssembly

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/miguelcc06/openclaw-docs-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server