Tigergraph

🚀 TG_MCP

A lightweight Python interface that exposes TigerGraph operations (queries, schemas, vertices, edges, UDFs) as structured tools and URI-based resources to the MCP agent.

🚀 Quick Start

TG_MCP is a lightweight Python interface that simplifies interacting with TigerGraph operations. It exposes various TigerGraph functionalities as structured tools and URI - based resources for MCP agents.

✨ Features

• Schema introspection Retrieve the complete graph schema (vertex and edge types).

• Query execution Run installed GSQL queries or raw GSQL strings with parameters.

• Vertex and edge insertion/updating Create or update vertices and edges.

• Resource URIs Access graph objects via tgraph://vertex/... and tgraph://query/... URIs.

• UDF and algorithm listing Obtain the catalog of installed user - defined functions and GDS algorithms.

📦 Installation

1. Clone the repository:

git clone [Repository URL]
cd TG_MCP

2. Create and activate a virtual environment (recommended):

python -m venv env
source env/bin/activate  # Use `env\Scripts\activate` on Windows

3. Install the dependencies:

pip install -r requirements.txt

📚 Documentation

Configuration

Set the following environment variables:

• TG_HOST: The address of the TigerGraph instance (e.g., http://localhost:14200).
• TG_GRAPH: The name of the graph to operate on.
• TG_SECRET: The access key for the TigerGraph REST API.

Example:

export TG_HOST="http://localhost:14200"
export TG_GRAPH="my_graph"
export TG_SECRET="your_api_secret_key"

Connecting to Claude

To connect this MCP server to Claude Desktop:

1. After installation, run the following command:

python -m tg_mcp.main install

2. Restart the client in Claude Desktop to apply the changes.

Project Structure

TG_MCP/
├── config.py            # Environment configuration (HOST, GRAPH, SECRET)
├── tg_client.py         # Wrapper for TigerGraphConnection and core operations
├── tg_tools.py          # `@mcp.tool` definitions to expose client methods
├── tg_resources.py      # `@mcp.resource` URI handlers
├── README.md            # Project documentation
└── requirements.txt     # List of dependencies

💻 Usage Examples

Basic Usage

from tg_mcp import TGClient

client = TGClient()
# Get the schema definition of vertices and edges
schema = client.get_schema()
print(schema)

Advanced Usage

result = client.execute_query("MATCH (a) RETURN a LIMIT 1")
print(result)

🤝 Contributing

To contribute to the project, follow these steps:

1. Fork the repository.
2. Create a feature branch: git checkout -b feature/your - feature - name.
3. Commit your changes: git add . && git commit -m "Your commit message".
4. Push to the remote repository: git push origin feature/your - feature - name.
5. Submit a pull request.

📄 License

This project is licensed under [License Name]. See the LICENSE file for details.