Provides tools for managing Google TPU (Tensor Processing Units) resources through the Google TPU API, enabling operations like creating, deleting, starting, stopping, and querying TPU nodes and accelerator types.
MCP Server
This project is an MCP (Multi-Agent Conversation Protocol) Server for the given OpenAPI URL - https://api.apis.guru/v2/specs/googleapis.com/tpu/v2/openapi.json, auto-generated using AG2's MCP builder.
Prerequisites
- Python 3.9+
- pip and uv
Installation
- Clone the repository:
- Install dependencies:
The .devcontainer/setup.sh script handles installing dependencies using
pip install -e ".[dev]"
. If you are not using the dev container, you can run this command manually.Alternatively, you can useuv
:
Development
This project uses ruff
for linting and formatting, mypy
for static type checking, and pytest
for testing.
Linting and Formatting
To check for linting issues:
To format the code:
These commands are also available via the scripts/lint.sh script.
Static Analysis
To run static analysis (mypy, bandit, semgrep):
This script is also configured as a pre-commit hook in .pre-commit-config.yaml.
Running Tests
To run tests with coverage:
This will run pytest and generate a coverage report. For a combined report and cleanup, you can use:
Pre-commit Hooks
This project uses pre-commit hooks defined in .pre-commit-config.yaml. To install the hooks:
The hooks will run automatically before each commit.
Running the Server
The MCP server can be started using the mcp_server/main.py script. It supports different transport modes (e.g., stdio
, sse
).
To start the server (e.g., in stdio mode):
The server can be configured using environment variables:
CONFIG_PATH
: Path to a JSON configuration file (e.g., mcp_server/mcp_config.json).CONFIG
: A JSON string containing the configuration.SECURITY
: Environment variables for security parameters (e.g., API keys).
Refer to the if __name__ == "__main__":
block in mcp_server/main.py for details on how these are loaded.
The tests/test_mcp_server.py file demonstrates how to start and interact with the server programmatically for testing.
Building and Publishing
This project uses Hatch for building and publishing. To build the project:
To publish the project:
These commands are also available via the scripts/publish.sh script.
This server cannot be installed
remote-capable server
The server can be hosted and run remotely because it primarily relies on remote services or has no dependency on the local environment.
Provides Multi-Agent Conversation Protocol access to Google Cloud TPU services, enabling management of Tensor Processing Units through natural language interactions with the Google TPU API.
Related MCP Servers
- AsecurityAlicenseAqualityA Model Context Protocol server that enables AI assistants like Claude to interact with Google Cloud Platform environments through natural language, allowing users to query and manage GCP resources during conversations.Last updated -9222134TypeScriptMIT License
- -securityAlicense-qualityEnables AI assistants to interact with and manage Google Cloud Platform resources including Compute Engine, Cloud Run, Storage, BigQuery, and other GCP services through a standardized MCP interface.Last updated -3PythonMIT License
- -securityFlicense-qualityA Multi-Agent Conversation Protocol server that enables interaction with Google Cloud Datastream API for managing data replication services between various source and destination systems through natural language commands.Last updated -Python
- -securityFlicense-qualityA Multi-Agent Conversation Protocol server for interacting with Google Play Game Services Configuration API, allowing management of game configurations through natural language commands.Last updated -Python