Metoro

Metoro is an MCP server that connects large language model interfaces to Metoro, an eBPF-based observability platform for Kubernetes environments. It enables developers, site reliability engineers, and DevOps teams to inspect cluster status and debug microservices directly through conversational assistants like Claude Desktop. The server interfaces with Metoro backend APIs, which collect telemetry generated by eBPF agents without requiring application code changes. By querying this server, users can retrieve overall cluster health summaries, view active namespaces, and inspect Kubernetes resources including pods, deployments, and daemonsets. It also provides deep microservice diagnostics by exposing service communication graphs, historical error patterns, and individual request traces. This allows operators to diagnose latency bottlenecks, investigate application exceptions, and explore workload topology without manually searching through dashboards or running repetitive command-line queries across their Kubernetes infrastructure.

Category: Cloud & Infrastructure

Tags: infrastructure, k8s, kubernetes, monitoring

Visit Metoro

How to install and configure Metoro

1. Ensure Golang is installed on your system using brew install go on macOS or sudo apt-get install golang on Ubuntu. 2. Clone the repository and navigate into the folder: git clone https://github.com/metoro-io/metoro-mcp-server.git && cd metoro-mcp-server. 3. Build the server executable: go build -o metoro-mcp-server. 4. Open your Claude Desktop configuration file at ~/Library/Application Support/Claude/claude_desktop_config.json. 5. Add the server entry with your binary path and API credentials: json { "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" } } } } 6. Save the file and restart Claude Desktop.

What you can do with Metoro

• Check the overall status and health score of a Kubernetes cluster using the get_cluster_health tool. - List all active namespaces, services, pods, deployments, and daemonsets across your running workloads. - Map microservice dependencies and inter-service communication patterns using the get_service_graph tool. - Inspect application error patterns and trace operational exceptions across connected Kubernetes services. - Retrieve specific distributed request traces to identify latency bottlenecks and diagnose performance degradations.

Key facts

• https://github.com/metoro-io/metoro-mcp-server
• Cloud & Infrastructure, Monitoring & Observability
• infrastructure, k8s, kubernetes, monitoring

Part of MCP Servers

What is Metoro MCP Server?

Metoro MCP Server is a Model Context Protocol server that connects Claude Desktop to the Metoro observability platform. It allows users to ask questions about their Kubernetes microservices and fetch telemetry generated via eBPF instrumentation.

How do I install Metoro MCP Server?

To install it, clone the GitHub repository, build the binary using go build -o metoro-mcp-server, and register the executable path inside your Claude Desktop configuration file alongside your Metoro authentication token and API URL.

Can I use Metoro MCP Server without an account?

Yes, you can test the server without an existing account by configuring the server to point to the live demo environment at demo.us-east.metoro.io using the publicly available demo token provided in the project repository.

Which MCP clients work with Metoro?

Metoro MCP Server is designed and tested for Claude Desktop, but it works with any Model Context Protocol client that supports local executable command-based server configurations and environment variable injection.

What tools does Metoro MCP Server provide?

The server includes tools such as get_cluster_health, get_namespaces, get_services, get_pods, get_deployments, get_daemonsets, get_service_graph, get_errors, and get_traces to inspect Kubernetes components and request telemetry.