MCP Server Exploration

Demonstrates a simple MCP server and client using the Connect API with an OpenAPI/Swagger workflow.

python

0

GitHub Stars

python

Language

7 months ago

First Indexed

3 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "mconflitti-pbc-mcp-server-exploration": {
      "command": "make",
      "args": [
        "server"
      ],
      "env": {
        "SWAGGER_FILE": "swagger.yaml",
        "CONNECT_API_KEY": "<your key>"
      }
    }
  }
}

You will learn how to run an MCP server that uses the Connect API and then connect a client to it. This setup lets you test end-to-end interactions between a local server and client, with the server driven by an OpenAPI/Swagger specification you provide.

How to use

To run the MCP server, set the required environment variables and start the server using the provided Make target. The server exposes its capabilities via the Swagger/OpenAPI specification you point to, and the client can connect to it to exercise the defined operations.

CONNECT_API_KEY="<your key>" SWAGGER_FILE="swagger.yaml" make server

After the server is running, start the MCP client to interact with the server you just launched. The client will use the server’s exposed operations to perform actions and return results.

make client

How to install

Prerequisites you need before installing and running the MCP server and client are a working shell, Python runtime, and Make available on your system.

Install and set up in your environment, then run the server and client as shown.

# Ensure you have a compatible shell and tools installed
# Example: verify Python and Make are available
python --version
make --version

Start the server with your API key and the path to the Swagger file, then start the client.

CONNECT_API_KEY="<your key>" SWAGGER_FILE="swagger.yaml" make server

make client

Notes and tips

You can customize the server by editing the main application to adjust the questions or prompts used in interactions. Modify the chat logic in your application code where the main function constructs prompts for the client.
The Swagger/OpenAPI integration shown registers tools and operations for use by the client. If you extend the API, regenerate the operation-to-tool mappings and re-register tools as needed.