TianGong AI Model Context Protocol (MCP) Server supports STDIO, SSE and StreamableHttp protocols.
npm install -g @tiangong-lca/mcp-server
npx dotenv -e .env -- \
npx -p @tiangong-lca/mcp-server tiangong-lca-mcp-stdionpm install -g @tiangong-lca/mcp-server
npm install -g supergateway
npx dotenv -e .env -- \
npx -y supergateway \
--stdio "npx -y -p @tiangong-lca/mcp-server tiangong-lca-mcp-stdio" \
--port 3001 \
--ssePath /sse --messagePath /message# Build MCP server image using Dockerfile (optional)
docker build -t linancn/tiangong-lca-mcp-server:0.0.5 .
# Pull MCP server image
docker pull linancn/tiangong-lca-mcp-server:0.0.5
# Start MCP server using Docker
docker run -d \
--name tiangong-lca-mcp-server \
--publish 9278:9278 \
--env-file .env \
linancn/tiangong-lca-mcp-server:0.0.5# 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# Format code using the linter
npm run lint# Launch the STDIO Server using MCP Inspector
npm start# 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-lca-mcp-server-0.0.5.tgz tiangong-lca-mcp-stdio" \
--port 3001 \
--ssePath /sse \
--messagePath /message
# Launch MCP Inspector
npx @modelcontextprotocol/inspectornpm login
npm run build && npm publishnpx tsx src/tools/openlca_ipc_test.ts