by metoro-io
Enables Claude Desktop App to retrieve Kubernetes telemetry data by exposing Metoro’s eBPF‑generated APIs to large language models.
Provides a bridge between the Claude Desktop application and a Kubernetes cluster, allowing LLMs to query real‑time observability data collected by Metoro’s eBPF agents.
go build -o metoro-mcp-server
.claude_desktop_config.json
in the Claude Desktop config folder and add an entry under mcpServers
that points to the compiled executable.METORO_AUTH_TOKEN
and METORO_API_URL
).Q: Do I need a Metoro account? A: No. You can use the public demo token that points to the demo cluster.
Q: Which environment variables are required?
A: METORO_AUTH_TOKEN
(your personal or demo token) and METORO_API_URL
(the Metoro endpoint).
Q: Can I run the server on Windows? A: The server is written in Go, so it can be compiled for any OS supported by Go, though the provided configuration examples target macOS/Linux.
Q: How does the server communicate with Claude Desktop? A: Via the Model Context Protocol (MCP), which the Claude Desktop app consumes to forward LLM requests to the server.
This repository contains th Metoro MCP (Model Context Protocol) Server. This MCP Server allows you to interact with your Kubernetes cluster via the Claude Desktop App!
You can read more about the Model Context Protocol here: https://modelcontextprotocol.io
But in a nutshell
The Model Context Protocol (MCP) is an open protocol that enables seamless integration between LLM applications and external data sources and tools. Whether you’re building an AI-powered IDE, enhancing a chat interface, or creating custom AI workflows, MCP provides a standardized way to connect LLMs with the context they need.
Metoro is an observability platform designed for microservices running in Kubernetes and uses eBPF based instrumentation to generate deep telemetry without code changes. The data that is generated by the eBPF agents is sent to Metoro's backend to be stored and in the Metoro frontend using our apis.
This MCP server exposes those APIs to an LLM so you can ask your AI questions about your Kubernetes cluster.
https://github.com/user-attachments/assets/b3f21e9a-45b8-4c17-8d8c-cff560d8694f
brew install go
for mac or sudo apt-get install golang
for ubuntu.git clone https://github.com/metoro-io/metoro-mcp-server.git
cd metoro-mcp-server
go build -o metoro-mcp-server
Copy your auth token from your Metoro account in Settings -> Users Settings.
Create a file in ~/Library/Application Support/Claude/claude_desktop_config.json
with the following contents:
{
"mcpServers": {
"metoro-mcp-server": {
"command": "<your path to Metoro MCP server go executable>/metoro-mcp-server",
"args": [],
"env": {
"METORO_AUTH_TOKEN" : "<your auth token>",
"METORO_API_URL": "https://us-east.metoro.io"
}
}
}
}
No worries, you can still play around using the Live Demo Cluster.
The included token is a demo token, publicly available for anyone to use.
Create a file in ~/Library/Application Support/Claude/claude_desktop_config.json
with the following contents:
{
"mcpServers": {
"metoro-mcp-server": {
"command": "<your path to Metoro MCP server go executable>/metoro-mcp-server",
"args": [],
"env": {
"METORO_AUTH_TOKEN" : "eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJjdXN0b21lcklkIjoiOThlZDU1M2QtYzY4ZC00MDRhLWFhZjItNDM2ODllNWJiMGUzIiwiZW1haWwiOiJ0ZXN0QGNocmlzYmF0dGFyYmVlLmNvbSIsImV4cCI6MTgyMTI0NzIzN30.7G6alDpcZh_OThYj293Jce5rjeOBqAhOlANR_Fl5auw",
"METORO_API_URL": "https://demo.us-east.metoro.io"
}
}
}
}
claude_desktop_config.json
save the file and restart Claude Desktop app.This server is built on top of our Golang MCP SDK.
Please log in to share your review and rating for this MCP.
{ "mcpServers": { "metoro-mcp-server": { "command": "/usr/local/bin/metoro-mcp-server", "args": [], "env": { "METORO_AUTH_TOKEN": "<YOUR_AUTH_TOKEN>", "METORO_API_URL": "https://us-east.metoro.io" } } } }
Discover more MCP servers with similar functionality and use cases
by netdata
Real-time, per‑second infrastructure monitoring platform that provides instant insights, auto‑discovery, edge‑based machine‑learning anomaly detection, and lightweight visualizations without requiring complex configuration.
by Arize-ai
Arize Phoenix is an open-source AI and LLM observability tool for inspecting traces, managing prompts, curating datasets, and running experiments.
by msgbyte
Provides website analytics, uptime monitoring, and server status in a single self‑hosted application.
by grafana
Provides programmatic access to Grafana dashboards, datasources, alerts, incidents, and related operational data through a Model Context Protocol server, enabling AI assistants and automation tools to query and manipulate Grafana resources.
by dynatrace-oss
Provides a local server that enables real‑time interaction with the Dynatrace observability platform, exposing tools for problem retrieval, DQL execution, Slack notifications, workflow automation, and AI‑assisted troubleshooting.
by pydantic
Provides tools to retrieve, query, and visualize OpenTelemetry traces and metrics from Pydantic Logfire via a Model Context Protocol server.
by VictoriaMetrics-Community
Access VictoriaMetrics instances through Model Context Protocol, enabling AI assistants and tools to query metrics, explore labels, debug configurations, and retrieve documentation without leaving the conversational interface.
by axiomhq
Axiom MCP Server implements the Model Context Protocol (MCP) for Axiom, enabling AI agents to query logs, traces, and other event data using the Axiom Processing Language (APL). It allows AI agents to perform monitoring, observability, and natural language analysis of data for debugging and incident response.
by GeLi2001
Datadog MCP Server is a Model Context Protocol (MCP) server that interacts with the official Datadog API. It enables users to access and manage various Datadog functionalities, including monitoring, dashboards, metrics, events, logs, and incidents.