Official · MODEL CONTEXT PROTOCOL

Ad Veritas mcp server trueRAG

Model Context Protocol (MCP) server to access an instance of TrueRAG

打开来源所有 MCP 服务器

连接能力

Ad Veritas mcp server trueRAG 为 AI Agent 提供什么

来源目录未提供结构化功能列表，请在使用前阅读源仓库文档。

安全

MCP 收录不等于安全审核

MCP 服务器可能获得模型上下文、凭据、本地文件或调用外部系统的权限。连接 Agent 前，请检查代码、环境变量、网络行为、软件包来源与维护状态。

README

仓库文档

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"
      ]
    }

在 GitHub 查看 README

社区

收藏、评分与讨论

正在载入社区数据…