Follow-along: Run the MCP server

3. Follow-along: Run the MCP server

Follow-along: Run the MCP server

🎯 Goal: Run the MCP server locally and use MCP Inspector to test a pre-defined tool.

Project structure

Open up the project folder in your code editor.

📂 workshop-mcp-intro
 ┣ 📂 operations
 ┣ ┗ 📄 GetFeaturedListings.graphql
 ┣ 📄 mcp.yaml
 ┣ 📄 router.yaml
 ┗ 📄 supergraph.yaml

We have a few config files and an operation file.

In mcp.yaml, we'll find the configuration for the MCP server.

mcp.yaml

operations:
  source: local
  paths:
    - ./operations/GetFeaturedListings.graphql

In supergraph.yaml, we'll find the configuration for the supergraph.

supergraph.yaml

federation_version: =2.11.0
subgraphs:
  listings:
    routing_url: https://rt-airlock-subgraphs-listings.herokuapp.com/
    schema:
      subgraph_url: https://rt-airlock-subgraphs-listings.herokuapp.com/
  # accounts:
  #   routing_url: https://rt-airlock-subgraphs-accounts.herokuapp.com/
  #   schema:
  #     subgraph_url: https://rt-airlock-subgraphs-accounts.herokuapp.com/
  # bookings:
  #   routing_url: https://rt-airlock-subgraphs-bookings.herokuapp.com/
  #   schema:
  #     subgraph_url: https://rt-airlock-subgraphs-bookings.herokuapp.com/
  # reviews:
  #   routing_url: https://rt-airlock-subgraphs-reviews.herokuapp.com/
  #   schema:
  #     subgraph_url: https://rt-airlock-subgraphs-reviews.herokuapp.com/
  # payments:
  #   routing_url: https://rt-airlock-subgraphs-payments.herokuapp.com/
  #   schema:
  #     subgraph_url: https://rt-airlock-subgraphs-payments.herokuapp.com/

We're working with just one service for now (listings). We'll open up the rest later on.

In router.yaml, we'll find minimal configuration for the local router. (Note the comment at the top of the file!)

Run the graph locally

To run the graph locally, we'll use the Rover CLI. Rover is Apollo's command line interface (CLI) tool that helps developers work with graphs.

Open a terminal and navigate to the root of the project.
Run the following command:
rover dev --supergraph-config supergraph.yaml --router-config router.yaml
We'll see some output in the terminal, with a successful message and the endpoint to get to our router in http://localhost:4000.
Navigate to http://localhost:4000 in the browser. We'll see the Apollo Sandbox connected to the endpoint, ready for us to query our local router.

Try running the following query:

query GetFeaturedListings {
  featuredListings {
    id
    title
    description
    costPerNight
    numOfBeds
    locationType
  }
}

We should see the data for the featured listings returned!

This is our graph working by itself, without any AI agents involved. Let's add the MCP server to the mix.

Run the graph and MCP server locally

Stop the rover dev command with Ctrl+C.

Run the same command but this time with the --mcp flag pointing to the mcp.yaml file.

rover dev --supergraph-config supergraph.yaml --router-config router.yaml --mcp mcp.yaml

We'll see some output in the terminal, with a successful message and the endpoint to get to our MCP server in http://127.0.0.1:5000.

Run the MCP Inspector

MCP Inspector is a tool that helps us inspect and debug MCP servers. It's a web-based tool that allows us to see the tools exposed by the server, and test them directly.

In a new terminal window, run the following command:

npx @modelcontextprotocol/inspector http://127.0.0.1:5000/mcp --transport http

This will open up a new tab in the browser to http://localhost:6274/.
Click the Connect button.
In the Tools tab, we should see the tools exposed by the server, and test them directly.
Click List Tools.
Right now, we only have one tool exposed: GetFeaturedListings. Click on it.
Click the Run Tool button.
We should see some data for the featured listings returned, the same ones we saw earlier when we ran the query against the local router.