k8s-observability-mcp
Verified Safeby martinimarcello00
Overview
Provides an MCP server to explore and analyze Kubernetes metrics, logs, traces, and service graph data for observability and debugging.
Installation
poetry run python mcp_server.pyEnvironment Variables
- TARGET_NAMESPACE
- PROMETHEUS_SERVER_URL
- JAEGER_URL
- NEO4J_URI
- NEO4J_USER
- NEO4J_PASSWORD
- TRACE_SERVICE_STARTING_POINT
- MCP_TRANSPORT
Security Notes
The server uses standard Python libraries for interacting with Kubernetes, Prometheus, Jaeger, and Neo4j, which generally use structured arguments or parameterized queries, mitigating common injection risks. Environment variables are used for configuration, preventing hardcoded credentials. A minor potential risk could arise if malicious input for pod names in Prometheus queries crafts a regex that causes performance issues, but this is less severe than direct code execution. The Neo4j graph creation/deletion functions are administrative and require manual file input or confirmation, not exposed to general user queries.
Similar Servers
mcp-server-kubernetes
Provides a Model Context Protocol (MCP) server for managing Kubernetes clusters via kubectl and Helm commands.
mcp-k8s
A Kubernetes MCP (Model Control Protocol) server that enables natural language interaction with Kubernetes clusters and Helm for resource and release management.
k8s-mcp-server
Provides a standardized Model Context Protocol (MCP) interface for interacting with and managing Kubernetes clusters and Helm releases, enabling automation and integration with CLI tools, web applications, and AI agents.
mcpcat-typescript-sdk
MCPcat is an analytics platform designed for MCP server owners to capture user intentions and behavior patterns, offering session replay, trace debugging, and integration with existing observability tools.