Marketing

MCP Server generated by mcp.ag2.ai

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": {
    "qingyun-wu-marketing-api": {
      "command": "python",
      "args": [
        "mcp_server/main.py",
        "stdio"
      ],
      "env": {
        "CONFIG": "{\"example_key\":\"value\"}",
        "SECURITY": "YOUR_API_KEYS",
        "CONFIG_PATH": "mcp_server/mcp_config.json"
      }
    }
  }
}

You run an MCP server that connects to the specified OpenAPI source to enable automated multi-agent conversations against the eBay Marketing API. This server is designed to be started locally, configured with environment variables, and operated with a client that can communicate via standard input/output (stdio). It supports development workflows and testing, and it includes tooling for linting, static analysis, and tests to keep your code healthy as you build integrations.

How to use

You interact with the MCP server from a client that speaks the Multi-Agent Conversation Protocol. Start the server in stdio mode to run locally and connect your client through the process I/O streams. Use this setup to test conversational flows, experiment with API endpoints, and validate multi-agent coordination against the target OpenAPI source.

How to install

Prerequisites: Python 3.9 or newer, plus pip and uv is used for development and running the server.

Clone the project directory.
Install dependencies for development.

pip install -e ".[dev]"

Alternatively, you can use uv to install in editable mode:

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

Additional configuration and running notes

Configure the MCP server with environment variables when you start it. The following variables influence how the server loads its configuration and security parameters.

CONFIG_PATH: Path to a JSON configuration file, for example mcp_server/mcp_config.json.
CONFIG: A JSON string containing the configuration.
SECURITY: Environment variables that define security parameters (for example, API keys or related secrets).

Starting and testing the server

To start the MCP server in stdio mode, run the following command.

python mcp_server/main.py stdio

Development tooling and quality checks

The project includes tooling to help you maintain code quality and reliability during development.

Linting and formatting with ruff: check and format code as needed.

ruff check
ruff format

Static analysis with mypy, bandit, and semgrep; run the provided script to perform all checks.

./scripts/static-analysis.sh

Run tests with coverage to ensure your changes don’t break existing behavior.

./scripts/test.sh
./scripts/test-cov.sh

Pre-commit hooks are enabled and run automatically before commits. Install them with:

pre-commit install

Building and publishing the project

Build and publish actions are supported through the package manager you use for Python projects.

hatch build
hatch publish

Available tools

lint

Linting and formatting with ruff to ensure code quality and consistency.

static-analysis

Static analysis with mypy, bandit, and semgrep to detect type issues and security risks.

tests

Running tests with pytest and generating a coverage report to verify functionality.

pre-commit

Pre-commit hooks that run on each commit to catch issues early.

start_server

Start the MCP server in stdio mode to enable client interactions via standard I/O.