A Model Context Protocol (MCP) server exposing an HTTP POST endpoint to access data from various open-access data publishers, developed for the EOSC Data Commons project.

It uses a search API, and a Large Language Model (LLM) to help users find the datasets and tools they need.

The HTTP API comprises 2 main endpoints:

• /mcp: MCP server that searches for relevant data to answer a user question using the EOSC Data Commons search API

  • Uses rmcp with Streamable HTTP transport
  • Available tools:
    • Search datasets
    • Search tools
    • Search citations related to datasets or tools

• /search: simple HTTP POST endpoint (JSON) for querying the MCP server via an LLM provider

  • Uses axum, utoipa for OpenAPI spec generation, llm to interact with LLM providers (e.g. Mistral, OpenAI)
  • Returns a streaming response: tool call requested, then tool call results, and final search results.

rustup update
cargo install cargo-release cargo-deny cargo-watch git-cliff

Create a .cargo/config.toml file with your Mistral API key or OpenAI API key:

[env]
MISTRAL_API_KEY = "YOUR_API_KEY"
OPENAI_API_KEY = "YOUR_API_KEY"

Start the MCP server in dev at http://localhost:8000/mcp, with OpenAPI UI at http://localhost:8000/docs

cargo run

Customize server configuration through CLI arguments:

cargo run -- --mcp-only --opensearch-url http://localhost:9200

Run and reload on change to the code:

cargo watch -x run

curl -X POST http://localhost:8000/search -H "Content-Type: application/json" -H "Authorization: SECRET_KEY" -d '{"messages": [{"role": "user", "content": "data insulin"}], "model": "mistral/mistral-small-latest", "stream": true}'

Follow the instructions of your client, and use the /mcp URL of your deployed server (e.g. http://localhost:8000/mcp)

Add a new MCP server through the VSCode UI:

• Open the Command Palette (ctrl+shift+p or cmd+shift+p)
• Search for MCP: Add Server...
• Choose HTTP, and provide the MCP server URL http://localhost:8000/mcp

Your VSCode mcp.json should look like:

{
    "servers": {
        "data-commons-mcp-server": {
            "url": "http://localhost:8000/mcp",
            "type": "http"
        }
    },
    "inputs": []
}

Build binary in target/release/

cargo build --release

./target/release/data-commons-mcp

Create a keys.env file with the API keys:

MISTRAL_API_KEY=YOUR_API_KEY
SEARCH_API_KEY=SECRET_KEY_YOU_CAN_USE_IN_FRONTEND_TO_AVOID_SPAM

Build and deploy the service:

docker compose up

Automatically format the codebase using rustfmt:

cargo fmt

Lint with clippy:

cargo clippy --all

Automatically apply possible fixes:

cargo clippy --fix

Check the dependency supply chain: licenses (only accept dependencies with OSI or FSF approved licenses), and vulnerabilities (CVE advisories).

cargo deny check

Update dependencies in Cargo.lock:

cargo update

Dry run:

cargo release patch

Or minor / major

Create release:

cargo release patch --execute