What is Api Discovery Service

The api-discovery-service is an MCP (Multi-Agent Conversation Protocol) Server that facilitates interaction with APIs defined in the OpenAPI specification. It is auto-generated using AG2’s MCP builder based on the provided OpenAPI URL.

Use cases

Use cases for the api-discovery-service include developing chatbots that interact with external APIs, creating multi-agent systems for data processing, and integrating various services into a cohesive application.

How to use

To use the api-discovery-service, clone the repository, install the necessary dependencies using pip or uv, and then run the server using the main script. The server can operate in various transport modes such as stdio and sse.

Key features

Key features of the api-discovery-service include automatic generation from OpenAPI specifications, support for multiple transport modes, linting and formatting tools, static analysis capabilities, and built-in testing frameworks.

Where to use

The api-discovery-service can be used in fields such as software development, API management, and any application requiring seamless communication between multiple agents or services.

MCP Server

This project is an MCP (Multi-Agent Conversation Protocol) Server for the given OpenAPI URL - https://api.apis.guru/v2/specs/googleapis.com/discovery/v1/openapi.json, auto-generated using AG2’s MCP builder.

Prerequisites

• Python 3.9+
• pip and uv

Installation

1. Clone the repository:

   git clone <repository-url>
   cd mcp-server
   

2. Install dependencies:
   The .devcontainer/setup.sh script handles installing dependencies using pip install -e ".[dev]". If you are not using the dev container, you can run this command manually.

   pip install -e ".[dev]"
   

   Alternatively, you can use uv:

   uv pip install --editable ".[dev]"
   

Development

This project uses ruff for linting and formatting, mypy for static type checking, and pytest for testing.

Linting and Formatting

To check for linting issues:

ruff check

To format the code:

ruff format

These commands are also available via the scripts/lint.sh script.

Static Analysis

To run static analysis (mypy, bandit, semgrep):

./scripts/static-analysis.sh

This script is also configured as a pre-commit hook in .pre-commit-config.yaml.

Running Tests

To run tests with coverage:

./scripts/test.sh

This will run pytest and generate a coverage report. For a combined report and cleanup, you can use:

./scripts/test-cov.sh

Pre-commit Hooks

This project uses pre-commit hooks defined in .pre-commit-config.yaml. To install the hooks:

pre-commit install

The hooks will run automatically before each commit.

Running the Server

The MCP server can be started using the mcp_server/main.py script. It supports different transport modes (e.g., stdio, sse).

To start the server (e.g., in stdio mode):

python mcp_server/main.py stdio

The server can be configured using environment variables:

• CONFIG_PATH: Path to a JSON configuration file (e.g., mcp_server/mcp_config.json).
• CONFIG: A JSON string containing the configuration.
• SECURITY: Environment variables for security parameters (e.g., API keys).

Refer to the if __name__ == "__main__": block in mcp_server/main.py for details on how these are loaded.

The tests/test_mcp_server.py file demonstrates how to start and interact with the server programmatically for testing.

Building and Publishing

This project uses Hatch for building and publishing.
To build the project:

hatch build

To publish the project:

hatch publish

These commands are also available via the scripts/publish.sh script.