grafeo-mcp

MCP server that exposes GrafeoDB - an embedded graph database - to AI agents via the Model Context Protocol.

One install, zero infrastructure. The MCP server is the database.

Features

• 23 tools - graph CRUD, GQL queries, batch import, full-text search, vector search, MMR, hybrid retrieval, PageRank, Dijkstra, Louvain and more
• 3 resources - graph://schema, graph://stats, graph://nodes/{id}
• 4 workflow prompts - guide agents through exploration, knowledge extraction, graph analysis and similarity search
• GQL with Cypher auto-normalization - agents trained on Cypher syntax work out of the box
• Schema-first - agents discover the graph structure before querying
• Token-aware - all tools have limit params and truncate large results
• Embedded - no separate database server to manage

Quickstart

# Install
uv tool install grafeo-mcp

# Or with pip
pip install grafeo-mcp

Claude Desktop

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "grafeo": {
      "command": "grafeo-mcp",
      "env": {
        "GRAFEO_DB_PATH": "/path/to/your/graph.db"
      }
    }
  }
}

Claude Code

Add to .mcp.json in your project root:

{
  "mcpServers": {
    "grafeo": {
      "command": "grafeo-mcp",
      "env": {
        "GRAFEO_DB_PATH": "./graph.db"
      }
    }
  }
}

VS Code / Copilot

Add to .vscode/mcp.json:

{
  "servers": {
    "grafeo": {
      "command": "grafeo-mcp",
      "env": {
        "GRAFEO_DB_PATH": "${workspaceFolder}/graph.db"
      }
    }
  }
}

HTTP transport

For remote or multi-client setups:

grafeo-mcp streamable-http

Environment Variables

Tools

Query

Graph CRUD & Traversal

Batch Import

Full-Text Search

Vector Search

Graph Algorithms

Resources

Prompts

Which tool when?

Batch reference syntax

The batch_import tool lets edges reference nodes created in the same batch using @N notation, where N is the zero-based index into the nodes array:

batch_import(
    nodes=[
        {"labels": ["Person"], "properties": {"name": "Alice"}},  # @0
        {"labels": ["Person"], "properties": {"name": "Bob"}},    # @1
    ],
    edges=[
        {"source_ref": "@0", "target_ref": "@1", "edge_type": "KNOWS"},
    ],
)

You can also mix batch references with existing node IDs: {"source_ref": "@0", "target_ref": 42, ...}.

Cypher normalization

The execute_gql tool automatically normalizes common Cypher syntax to GQL so agents trained on Cypher work out of the box. Currently the following transformations are applied:

Keywords that are shared between Cypher and GQL (such as MATCH, RETURN, WHERE, WITH, LIMIT, DETACH DELETE) pass through unchanged. Cypher-only keywords like MERGE or OPTIONAL MATCH are not supported and will produce a clear error message from the query engine.

Development

git clone https://github.com/GrafeoDB/grafeo-mcp
cd grafeo-mcp
uv sync
uv run pytest          # Run tests
uv run ruff check .    # Lint
uv run ruff format .   # Format
uv run ty check        # Type check

See Also

• [grafeo-memory](https://github.com/GrafeoDB/grafeo-memory) includes a built-in MCP server (grafeo-memory-mcp) that wraps the high-level memory API — extract, reconcile, search, summarize. If you need AI memory management rather than raw graph access, use uv add grafeo-memory[mcp].

License

Apache-2.0