The TianGong-LCA-MCP Server provides advanced search capabilities and supports multiple interaction protocols:

• Hybrid Search with Context Extension: Perform searches in Weaviate with parameters for query, collection, topK results, and context extensions (extK).

• ESG Database Search: Execute searches on an Environmental, Social, and Governance database with filtering options by record ID, country, date ranges, and metadata keywords.

• Multiple Protocol Support: Interact with the server via STDIO, SSE (Server-Sent Events), and StreamableHttp protocols, enabling flexible integration options.

• Deployment Options: Easy deployment via npm, Docker, or local development setup.

Allows containerized deployment of the MCP server using Docker, with configuration through environment variables and port publishing.

Enables configuration of the MCP server through environment variables loaded from .env files.

Provides the runtime environment for the MCP server with version management support.

Handles package installation, dependency management, and publishing for the MCP server.

Manages Node.js versions for development and execution of the MCP server.

1. Click on "Install Server".

2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.

3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@TianGong-LCA-MCP Server calculate the carbon footprint of producing 1kg of steel"

That's it! The server will respond to your query, and you can continue using it as needed.

Here is a step-by-step guide with screenshots.

GLAD_API_KEY=your-glad-api-key
GLAD_API_BASE_URL=https://www.globallcadataaccess.org/api/v1

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

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

# 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

# Launch the STDIO Server using MCP Inspector
npm start

npm run start:server

npm run start:server-local

DANGEROUSLY_OMIT_AUTH=true npx @modelcontextprotocol/inspector

Looking for Admin?