graphql interface for mcp

Model Context Protocol (MCP) Server for GraphQL Policies API

This repository contains a Model Context Protocol (MCP) server implementation for a GraphQL API that provides access to policies.

The server is built using the python SDK for MCP and uses the GQL library to interact with the GraphQL API.

Getting Started

Clone the repository

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

Make sure you have uv installed

uv --version

If not, you can install it using:

# On macOS and Linux.
curl -LsSf https://astral.sh/uv/install.sh | sh

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

Define the environment variables

The server is configured to work against a GraphQL API for one of the TrueRag systems. Once you created the TrueRAG environment, copy the API key and endpoint from the environment variables.

Create a .env file in the root directory of the repository and add the following lines:

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

Add to the MCP Client, such as Claude Desktop

Add the following lines to the Claude configuration file (~/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"
      ]
    }

MCP Server · Populars

MCP Server · New

    render-oss

    Render MCP Server

    The Official Render MCP Server

    Community render-oss
    nhevers

    claude-recall

    Long-term memory layer for Clawd & Claude Code that learns and recalls your project context automatically

    Community nhevers
    VienLi

    lark-tools-mcp

    MCP server provides Feishu related operations to AI encoding agents such as cursor 飞书MCP插件,读取文档、发送消息、合同审批、数据处理.....

    Community VienLi
    joeseesun

    🎯 多源内容 → NotebookLM 智能处理器

    Claude Skill: Multi-source content processor for NotebookLM. Supports WeChat articles, web pages, YouTube, PDF, Markdown, search queries → Podcast/PPT/MindMap/Quiz etc.

    Community joeseesun
    avivsinai

    Langfuse MCP Server

    A Model Context Protocol (MCP) server for Langfuse, enabling AI agents to query Langfuse trace data for enhanced debugging and observability

    Community avivsinai