What is Tiangong Ai Mcp

TianGong-AI-MCP is a server that implements the TianGong AI Model Context Protocol (MCP), supporting both STDIO and SSE protocols for communication.

Use cases

Use cases include deploying AI models for chatbots, real-time analytics applications, and any system requiring efficient data streaming and processing.

How to use

To use TianGong-AI-MCP, you can start the server using STDIO or set up a remote SSE server. You can also run it using Docker for containerized deployment.

Key features

Key features include support for STDIO and SSE protocols, easy setup with Docker, and the ability to run locally or remotely.

Where to use

TianGong-AI-MCP can be used in various fields such as AI model deployment, real-time data processing, and interactive applications that require efficient communication protocols.

TianGong-AI-MCP

中文 | English

TianGong AI Model Context Protocol (MCP) Server supports both STDIO, SSE and Streamable Http protocols.

Starting MCP Server

Client STDIO Server

npm install -g @tiangong-ai/mcp-server

npx dotenv -e .env -- \
npx -p @tiangong-ai/mcp-server tiangong-ai-mcp-stdio

Remote SSE Server

npm install -g @tiangong-ai/mcp-server
npm install -g supergateway

npx dotenv -e .env -- \
npx -y supergateway \
    --stdio "npx -y -p @tiangong-ai/mcp-server tiangong-ai-mcp-stdio" \
    --port 3001 \
    --ssePath /sse --messagePath /message

Using Docker

# Build MCP server image using Dockerfile (optional)
docker build -t linancn/tiangong-ai-mcp-server:0.0.13 .

# Pull MCP server image
docker pull linancn/tiangong-ai-mcp-server:0.0.13

# Start MCP server using Docker
docker run -d \
    --name tiangong-ai-mcp-server \
    --publish 9277:9277 \
    --env-file .env \
    linancn/tiangong-ai-mcp-server:0.0.13

Development

Environment Setup

# Install Node.js
curl -o- https://raw.githubusercontent.com/nvm-sh/nvm/v0.40.2/install.sh | bash
nvm install 22
nvm use

# Install dependencies
npm install

# Update dependencies
npm update && npm ci

Code Formatting

# Format code using the linter
npm run lint

Local Testing

STDIO Server

# Launch the STDIO Server using MCP Inspector
npm start

SSE Server

# Build and package the project
npm run build && npm pack

# Optionally, install supergateway globally
npm install -g supergateway

# Launch the SSE Server (If the parameter --baseUrl is configured, it should be set to a valid IP address or domain name)
npx dotenv -e .env -- \
npx -y supergateway \
    --stdio "npx -y -p tiangong-ai-mcp-server-0.0.13.tgz tiangong-ai-mcp-stdio" \
    --port 3001 \
    --ssePath /sse \
    --messagePath /message

# Launch MCP Inspector
npx @modelcontextprotocol/inspector

Publishing

npm login

npm run build && npm publish