logo
Free, unlimited AI code reviews that run on commit
git-lrc git-lrc GitHub Install Now We'd appreciate a star git-lrc - Free, unlimited AI code reviews that run on commit | Product Hunt git-lrc - Free, unlimited AI code reviews that run on commit | Product Hunt

mcp-gql-policy-gateway

A service gateway engineered for Model Context Protocol (MCP) interactions, exposing organizational governance policies via a GraphQL endpoint. This implementation leverages the official Python SDK for MCP alongside the GQL framework for robust API communication.

Author

mcp-gql-policy-gateway logo

Ad-Veritas

No License

Quick Info

GitHub GitHub Stars 2
NPM Weekly Downloads 0
Tools 1
Last Updated 2026-02-19

Tags

graphqlprotocolapipolicies graphqlcontext protocolgraphql api

Model Context Protocol (MCP) Gateway for Policy Retrieval via GraphQL

This repository furnishes a server component implementing the Model Context Protocol (MCP) standards, specifically configured to serve organizational governance policies through a dedicated GraphQL interface.

The core logic relies upon the established python SDK for MCP and utilizes the capabilities of the GQL library for handling all GraphQL endpoint communications.

Initial Setup Procedure

Repository Acquisition

Execute the following commands to clone the source code:

git clone https://github.com/Ad-Veritas/mcp-server-trueRAG.git
cd mcp-server-trueRAG

Prerequisite: Install the 'uv' Package Manager

Confirm that the uv tool is present on your system:

uv --version

If 'uv' is absent, installation can proceed using these platform-specific instructions:

# For Unix-like systems (macOS/Linux).
curl -LsSf https://astral.sh/uv/install.sh | sh

# For Windows operating systems.
powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"

Configure Environment Variables

The server is pre-set to target a GraphQL API instance associated with a TrueRag deployment. After establishing your TrueRAG operational environment, procure the necessary API key and service endpoint details.

Create a configuration file named .env in the repository's primary directory and populate it with the following variables:

GRAPHQL_API_KEY = "{your_api_key}"
GRAPHQL_ENDPOINT = "{your_graphql_endpoint}"

Integration with MCP Client Applications (e.g., Claude Desktop)

To permit client applications like Claude Desktop to resolve policies via this gateway, append the subsequent configuration stanza to the client's configuration file (e.g., ~/Library/Application Support/Claude/claude_desktop_config.json):

    "shipping-policies": {
      "command": "uv",
      "args": [
        "--directory",
        "{path_to_mcp_server}/mcp-server-trueRAG",
        "run",
        "fastmcp",
        "run",
        "server.py"
      ]
    }

See Also

`