home / mcp / datastream api mcp server

Datastream 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-datastream-api": {
      "command": "python",
      "args": [
        "mcp_server/main.py",
        "stdio"
      ],
      "env": {
        "CONFIG": "{...JSON CONFIG...}",
        "SECURITY": "API_KEYS",
        "CONFIG_PATH": "mcp_server/mcp_config.json"
      }
    }
  }
}

This MCP server exposes a Model Context Protocol interface for the Google Datastream v1 API, enabling you to manage model contexts and interactions through a defined MCP channel. It is designed to be run locally or in your development environment, and it can be configured via environment variables or a JSON configuration file to suit your security and deployment needs.

How to use

You connect an MCP client to this server to perform model-context operations against the Google Datastream v1 API. Start the server in a standard runtime mode, then load your MCP configuration to point to the Datastream API. Use the client to send requests that create, update, or query model contexts, and receive responses through the MCP channel. If you are testing locally, you can run the server in a straightforward local mode and provide configuration via environment variables or a config file.

How to install

Prerequisites: Python 3.9+ and pip. You will also use uv for local development if you prefer a lightweight runner.

# Prerequisites
python3.9 --version
pip --version

# Optional: install uv for a lightweight runner
pip install uv

1. Install development dependencies so you can run and test the MCP server locally.

pip install -e ".[dev]"

2. If you are not using a development container, install dependencies manually with the same command above.

pip install -e ".[dev]"

3. Run the MCP server in a standard I/O configuration to interact with clients locally.

python mcp_server/main.py stdio

Additional sections

Configuration and environment variables provide control over how the server loads its settings and where it looks for its runtime data. The following environment variables are commonly used to configure the server at runtime:

- 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 for security parameters (for example, API keys).

Running tests and development tooling

The project uses linting, static type checking, and testing tools to ensure code quality during development.

ruff check
ruff format
./scripts/static-analysis.sh
./scripts/test.sh
(pre-commit hooks are configured; run `pre-commit install` to enable)

Build and publishing

Build and publish workflows are typically handled by the project’s build system. Use the provided build and publish commands to create distributable artifacts if you plan to share or deploy the MCP server.

Available tools

start

Launch the MCP server in stdio mode to listen for MCP client interactions.

load_config

Load configuration from a JSON file or environment variable to customize behavior.