Skip to main content

The first zero-trust, air-gapped Enterprise GraphRAG server for the Model Context Protocol (MCP).

Project description

VeritasGraph MCP Server

The first zero-trust, air-gapped Enterprise GraphRAG server for the Model Context Protocol.

Connect your local IDE agent — Claude Desktop, Cursor, VS Code, Windsurf, Cline, Continue — directly to the VeritasGraph knowledge-graph engine over a standard JSON-RPC 2.0 stdio stream. Build graphs from your documents, run multi-hop graph-grounded queries with verifiable [doc#chunk] citations, and inspect entities — all 100% locally, with zero external data egress.

  • Zero-trust / air-gapped — stdlib-only JSON-RPC server; no cloud calls, no telemetry. The only network hop is your local Ollama runtime.
  • Verifiable attribution — every node and edge records the source chunk it came from, so answers cite their evidence.
  • Drop-in — wraps the same studio_api.graphrag_engine used by Studio.

Tools

Tool Purpose
veritasgraph_ingest_document Chunk a document, extract entities/relationships, merge into the graph.
veritasgraph_query Multi-hop, graph-grounded answer with citations and reasoning path.
veritasgraph_search_entities Fast subgraph retrieval for a query (no LLM call).
veritasgraph_get_graph Return the full graph: nodes, edges, stats.
veritasgraph_clear_graph Clear the entire graph (destructive).

Resources

URI Description
veritasgraph://graph Live snapshot of the knowledge graph.
veritasgraph://stats Entity / relationship / source counts.

Requirements

  • Python 3.10+

  • VeritasGraph repo dependencies: pip install -r requirements.txt

  • A local Ollama runtime with a chat model pulled (ingest/query need a model; search_entities/get_graph do not):

    ollama serve & ollama pull qwen3:latest
    

Run it

# From the repository root
python -m veritasgraph_mcp            # stdio JSON-RPC server
python -m veritasgraph_mcp --debug    # verbose logging on stderr

Environment variables

Variable Default Meaning
VERITASGRAPH_MODEL qwen3:latest Default Ollama model for ingest/query.
OLLAMA_HOST 127.0.0.1:11434 Local Ollama endpoint.
STUDIO_DATA_DIR studio_api/data Where the graph snapshot is persisted.

Register in your IDE

Replace /abs/path/to/VeritasGraph with the absolute path to your clone, and point command at the repo's Python (e.g. .venv/bin/python).

Claude Desktop — claude_desktop_config.json

{
  "mcpServers": {
    "veritasgraph": {
      "command": "/abs/path/to/VeritasGraph/.venv/bin/python",
      "args": ["-m", "veritasgraph_mcp"],
      "cwd": "/abs/path/to/VeritasGraph",
      "env": { "VERITASGRAPH_MODEL": "qwen3:latest" }
    }
  }
}

Cursor — .cursor/mcp.json

{
  "mcpServers": {
    "veritasgraph": {
      "command": "/abs/path/to/VeritasGraph/.venv/bin/python",
      "args": ["-m", "veritasgraph_mcp"],
      "cwd": "/abs/path/to/VeritasGraph"
    }
  }
}

VS Code — .vscode/mcp.json

{
  "servers": {
    "veritasgraph": {
      "type": "stdio",
      "command": "/abs/path/to/VeritasGraph/.venv/bin/python",
      "args": ["-m", "veritasgraph_mcp"],
      "cwd": "/abs/path/to/VeritasGraph"
    }
  }
}

Windsurf, Cline, and Continue use the same command / args / cwd shape.


Quick manual test (no IDE)

Pipe raw JSON-RPC frames over stdio:

printf '%s\n' \
  '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{}}' \
  '{"jsonrpc":"2.0","id":2,"method":"tools/list","params":{}}' \
  '{"jsonrpc":"2.0","id":3,"method":"tools/call","params":{"name":"veritasgraph_get_graph","arguments":{}}}' \
  | python -m veritasgraph_mcp

You should get three JSON-RPC responses: server info, the tool catalog, and the current graph snapshot.


How it fits VeritasGraph

The MCP server is a thin protocol adapter. All graph construction, multi-hop retrieval, and citation logic live in studio_api/graphrag_engine.py, the same engine that powers Studio. That means the MCP surface, the Studio UI, and the HTTP API all read and write the same local knowledge graph.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

veritasgraph_mcp-0.1.0.tar.gz (52.4 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

veritasgraph_mcp-0.1.0-py3-none-any.whl (37.0 kB view details)

Uploaded Python 3

File details

Details for the file veritasgraph_mcp-0.1.0.tar.gz.

File metadata

  • Download URL: veritasgraph_mcp-0.1.0.tar.gz
  • Upload date:
  • Size: 52.4 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.12.3

File hashes

Hashes for veritasgraph_mcp-0.1.0.tar.gz
Algorithm Hash digest
SHA256 1632fb609ab10a33882ef9fbe3b4f30234f3120369de6a4c04ad7d4e8565b19b
MD5 c1bb5293a343e3df8a82b1189d6cb49f
BLAKE2b-256 e4b85abd402bfb7f6e4497df688b3b04ab0c6dc47192bffee0d55d5eeacc1c91

See more details on using hashes here.

File details

Details for the file veritasgraph_mcp-0.1.0-py3-none-any.whl.

File metadata

File hashes

Hashes for veritasgraph_mcp-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 b6ae3843bf6c10bd4054ccb509bb489369809fd7cb21bc67a9c5f893e096ebda
MD5 499191443364fdd94d6c034e824ed583
BLAKE2b-256 d3ed9cdf8b06171748bbd58455356afa8b755e2eef014a44767b244ae7adfbda

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page