gcp-telemetry-mcp

kitagry/gcp-telemetry-mcp

3.4

If you are the rightful owner of gcp-telemetry-mcp and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to henry@mcphub.com.

A Model Context Protocol (MCP) server for Google Cloud Platform telemetry services, providing seamless integration with GCP observability tools.

The GCP Telemetry MCP Server is designed to facilitate the integration of Google Cloud Platform's observability tools, such as Cloud Logging, Cloud Monitoring, Cloud Trace, and Cloud Profiler, into a cohesive telemetry service. This server allows users to write, list, and manage log entries, create and query custom metrics, analyze distributed traces, and profile applications with ease. By leveraging the power of Google Cloud's APIs, the server provides a robust solution for monitoring and analyzing application performance and behavior. It supports advanced features like structured logging, custom metric descriptors, time series data management, trace span updates, and profiling sessions, making it an essential tool for developers and operations teams looking to enhance their cloud-based applications' observability.

Features

  • Structured logging with multiple severity levels and custom labels.
  • Custom metric descriptor creation and time series data management.
  • Advanced trace analysis with filtering, pagination, and span updates.
  • Profiling sessions for various profile types including CPU and HEAP.
  • Seamless integration with Google Cloud's authentication and APIs.

Usages

usage with local integration stdio

python
mcp.run(transport='stdio')  # Tools defined via @mcp.tool() decorator

usage with local integration subprocess

python
command='uv', args=['run', 'server.py']  # Launch using virtual environment

usage with remote integration sse

python
mcp.run(transport='sse', host="0.0.0.0", port=8000)  # Specify SSE endpoint

usage with remote integration streamable http

yaml
paths:
  /mcp:
    post:
      x-ms-agentic-protocol: mcp-streamable-1.0  # Copilot Studio integration

usage with platform integration github

{"command": "docker", "args": ["run", "-e", "GITHUB_PERSONAL_ACCESS_TOKEN", "ghcr.io/github/github-mcp-server"]}

usage with platform integration fastmcp

python
from mcp.server import FastMCP
app = FastMCP('demo')
@app.tool()
async def query(): ...

Tools

  1. write_log_entry

    Write a log entry to Cloud Logging with structured data and custom labels.

  2. list_log_entries

    List log entries from Cloud Logging with filtering and pagination.

  3. create_metric_descriptor

    Create a custom metric descriptor in Cloud Monitoring.

  4. write_time_series

    Write time series data to Cloud Monitoring.

  5. list_time_series

    List time series data from Cloud Monitoring with advanced filtering.