home / mcp / datastore mcp server

Datastore MCP Server

MCP Server generated by mcp.ag2.ai

Installation

Add the following to your MCP client configuration file.

Configuration

{
  "mcpServers": {
    "ag2-mcp-servers-cloud-datastore-api": {
      "url": "https://api.apis.guru/v2/specs/googleapis.com/datastore/v1beta1/openapi.json",
      "headers": {
        "CONFIG": "{...}",
        "SECURITY": "YOUR_API_KEY",
        "CONFIG_PATH": "mcp_server/mcp_config.json"
      }
    }
  }
}

You run an MCP Server that exposes a context-aware API for the Google Datastore OpenAPI definition. It lets you connect clients via standard MCP transports and load configuration from environment variables or a JSON config, enabling streamlined model-context communication for your applications.

How to use

Start the MCP server in a mode that suits your workflow, then connect your MCP client to it. The server supports multiple transport modes, such as stdio for local development, SSE for streaming, or streamable HTTP for remote communication. You control behavior through environment configuration or a JSON config to tailor security, endpoints, and runtime options.

How to install

Prerequisites include Python 3.9 or newer, plus the tools needed to run the server locally.

Clone the project and move into the server directory.

git clone <repository-url>
cd mcp-server

Install development dependencies so you can run and test the server locally. You have two common options:

pip install -e ".[dev]"
```
or
```
uv pip install --editable ".[dev]"

Alternative approach using uv to install editable dependencies is also supported.

Run the server in stdio mode to start interacting directly with your local processes.

python mcp_server/main.py stdio

Additional configuration and notes

The server can read configuration from environment variables or a JSON config file. The important variables are:

- CONFIG_PATH: Path to a JSON configuration file, for example mcp_server/mcp_config.json.

- CONFIG: A JSON string containing the server configuration.

- SECURITY: Environment variables related to security, such as API keys.

Available tools

lint

Run linting and formatting to ensure code quality. Use ruff for linting and formatting, and run the provided lint scripts.

static-analysis

Execute static analysis tools to catch vulnerabilities and code smells, including mypy, bandit, and semgrep as configured.

tests

Run tests with coverage to verify functionality. Commands include test and test-cov scripts.

pre-commit

Install and run pre-commit hooks to enforce code quality before commits.

build

Build the MCP server package for publishing or distribution using the project’s build tools.

publish

Publish the built MCP artifacts to your package registry or repository.

server-run

Start the MCP server in a supported transport mode (stdio in this example) and connect MCP clients to it.