home / mcp / workflows api mcp server

Workflows API MCP Server

MCP Server generated by mcp.ag2.ai

Installation

Add the following to your MCP client configuration file.

Configuration

{
  "mcpServers": {
    "ag2-mcp-servers-workflows-api": {
      "command": "python",
      "args": [
        "mcp_server/main.py",
        "stdio"
      ],
      "env": {
        "CONFIG": "JSON string with configuration",
        "SECURITY": "Security parameters like API keys",
        "CONFIG_PATH": "Path to JSON configuration (e.g., mcp_server/mcp_config.json)"
      }
    }
  }
}

You run an MCP server that exposes the Model Context Protocol interface for the Google Workflows API specification. This server lets you connect an MCP client to the OpenAPI-driven workflows service, enabling context-aware queries and actions against that API in a structured, consistent way.

How to use

To use the MCP server, start it in stdio mode and connect your MCP client to the provided command interface. The server reads configuration from environment variables or a JSON file you provide, and it serves the MCP protocol over standard input/output.

How to install

Prerequisites you need before installation are Python 3.9 or later, and either pip or uv to run the server locally.

Step 1: Clone the project directory and navigate into it.

git clone <repository-url>
cd mcp-server

Step 2: Install dependencies. Use the development extras to ensure all tooling is available.

pip install -e ".[dev]"

If you prefer using uv to install the development package, you can run this instead.

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

Step 3: Start the MCP server in stdio mode. This runs a local server you can connect to with MCP clients.

python mcp_server/main.py stdio

Additional configuration and notes

You can customize how the server loads its configuration using environment variables.

Environment variables you can set include:

- 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 (such as API keys).

Available tools

ruff

Lints and formats the codebase to maintain clean, consistent style and catch potential issues.

static analysis

Runs static analysis tools (mypy, bandit, semgrep) to detect type errors, security issues, and code quality problems.

pytest

Executes test suites to validate functionality and ensure changes do not break existing behavior.

pre-commit

Runs a suite of checks before each commit to enforce code quality and consistency.

mcp server runtime

Starts the MCP server in stdio mode so that MCP clients can connect over standard input/output.