TG_MCP
A lightweight Python interface that exposes TigerGraph database operations as structured tools and URI-based resources for Claude and other MCP agents.
README
TG_MCP
A lightweight Python interface that exposes TigerGraph operations (queries, schema, vertices, edges, UDFs) as structured tools and URI-based resources for MCP agents.
Table of Contents
- Features
- Project Structure
- Installation
- Configuration
- Connecting to Claude
- Examples
- Contributing
- License
Features
-
Schema Introspection
Retrieve full graph schema (vertex & edge types). -
Query Execution
Run installed GSQL queries or raw GSQL strings with parameters. -
Vertex & Edge Upsert
Create or update vertices and edges programmatically. -
Resource URIs
Access graph objects throughtgraph://vertex/...andtgraph://query/...URIs. -
UDF & Algorithm Listing
Fetch installed user-defined functions and GDS algorithm catalogs.
Project Structure
TG_MCP/
├── config.py # Environment config (HOST, GRAPH, SECRET)
├── tg_client.py # Encapsulates TigerGraphConnection and core operations
├── tg_tools.py # `@mcp.tool` definitions exposing client methods
├── tg_resources.py # `@mcp.resource` URI handlers
├── main.py # MCP app bootstrap (`mcp.run()`)
├── pyproject.toml # Project metadata & dependencies
├── LICENSE # MIT License
└── .gitignore # OS/Python ignore rules
Installation
-
Clone the repo
git clone https://github.com/Muzain187/TG_MCP.git cd TG_MCP -
Create & activate a virtual environment
python3 -m venv venv source venv/bin/activate -
Install dependencies
pip install .Requires
mcp[cli]>=1.6.0andpyTigerGraph>=1.8.6.
Configuration
Set the following environment variables before running:
export TG_HOST=https://<your-tigergraph-host>
export TG_GRAPH=<your-graph-name>
export TG_SECRET=<your-api-secret>
These are read by config.py.
Connecting to Claude
This MCP server can be installed into the Claude Desktop client so that Claude can invoke your TigerGraph tools directly:
uv run mcp install main.py
After running the above, restart Claude Desktop and you’ll see your MCP tools available via the hammer 🛠 icon.
Examples:
Contributing
- Fork the repository
- Create a feature branch
git checkout -b feature/YourFeature - Commit your changes
git commit -m "Add YourFeature" - Push to branch
git push origin feature/YourFeature - Open a Pull Request
Please ensure all new code is covered by tests and follows PEP-8 style.
License
This project is licensed under the MIT License.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。
mcp-server-qdrant
这个仓库展示了如何为向量搜索引擎 Qdrant 创建一个 MCP (Managed Control Plane) 服务器的示例。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。