Cloud Private Catalog

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": {
    "ag2-mcp-servers-cloud-private-catalog": {
      "command": "python",
      "args": [
        "mcp_server/main.py",
        "stdio"
      ],
      "env": {
        "CONFIG": "{\"transport\":\"stdio\"}",
        "SECURITY": "YOUR_API_KEY",
        "CONFIG_PATH": "mcp_server/mcp_config.json"
      }
    }
  }
}

You run an MCP Server that exposes a programmable context protocol based on a provided OpenAPI specification. This server lets clients query and interact with the Google Cloud Private Catalog data model in a standardized way, enabling consistent integration and automation across environments.

How to use

Start the MCP server in stdio mode to enable local, in-process communication with MCP clients. The server reads its configuration from environment variables and can be started directly from your console. Once running, you connect to it using an MCP client in the transport mode you prefer (stdio, sse, or streamable-http) and perform operations that reflect the underlying Cloud Private Catalog data model.

How to install

Prerequisites: Python 3.9+; ensure you have pip and the uv tool installed.

Clone the project repository.
Change into the project directory.
Install development dependencies.
Run tests or start the server as needed.

Additional configuration and notes

Configure the server using environment variables. The following variables are recognized:

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 carry security parameters such as API keys.

If you want to use a pre-defined development environment, you can rely on the project’s development tooling to validate code quality, static analysis, and tests before starting the server.

Build and run references

Build and packaging uses Hatch. You can build and publish your MCP server distribution with Hatch commands.

To build the project:

hatch build

To publish the project:

hatch publish

Available tools

ruff

Lints and formats Python code to ensure consistency and quality.

mypy

Performs static type checking to catch type errors early.

pytest

Runs unit and integration tests to verify behavior.

pre-commit

Runs a collection of checks before committing changes to ensure code quality.

hatch

Builds and publishes the MCP server package.