# Docs MCP server

Memgraph provides a public MCP server for its documentation. Connect it to any
MCP-capable AI assistant to ask questions about Memgraph and get answers
grounded in the current docs, with sources. There is no API key or sign-in
required, just one endpoint.

- **Endpoint:** `https://mcp-docs.memgraph.com`
- **Tool provided:** `search_memgraph_knowledge_sources`

The **Connect AI** button in the docs navbar shows the setup for each client
and installs the server in Cursor or VS Code in one click.

This server searches the documentation. To let an agent query your own
Memgraph database, use the [Memgraph MCP server](https://memgraph.com/docs/ai-ecosystem/integrations/mcp) instead.

## Connect your client

### Claude Code

```bash
claude mcp add --transport http memgraph-docs https://mcp-docs.memgraph.com
```

### Codex

Codex connects through the `mcp-remote` bridge, which needs Node.js:

```bash
codex mcp add memgraph-docs -- npx -y mcp-remote@latest https://mcp-docs.memgraph.com
```

### Cursor

Add to `~/.cursor/mcp.json`, or to `.cursor/mcp.json` in your project:

```json
{
  "mcpServers": {
    "memgraph-docs": {
      "url": "https://mcp-docs.memgraph.com"
    }
  }
}
```

### VS Code

Add to `.vscode/mcp.json`:

```json
{
  "servers": {
    "memgraph-docs": {
      "type": "http",
      "url": "https://mcp-docs.memgraph.com"
    }
  }
}
```

### Claude Desktop and other stdio-only clients

These clients need Node.js and the `mcp-remote` bridge:

```json
{
  "mcpServers": {
    "memgraph-docs": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote@latest",
        "https://mcp-docs.memgraph.com"
      ]
    }
  }
}
```

After adding it, restart your client and ask a Memgraph question. The assistant
looks up the relevant documentation.

> **Info**
>
> The assistant answers from the current docs with links, so you can follow up
>   with "show me the exact config" or "give me the full working example" and it
>   will pull the specifics.

## Example prompts

Once connected, ask your assistant questions in plain language. It calls the
docs server and answers with sources. For example:

- "How do I install Memgraph with Docker and connect to it from Python?"
- "I'm coming from Neo4j. What Cypher differences should I know about in
  Memgraph?"
- "My traversal query is slow. How do I read a query plan with EXPLAIN and
  PROFILE, and what do I optimize first?"
- "How do I configure durability with snapshots and WAL so I don't lose data
  on restart?"
- "How do I run PageRank and community detection on my graph?"
- "How do I combine vector search with a multi-hop traversal to ground an LLM
  answer in my knowledge graph?"