Side-by-side comparison of two Model Context Protocol servers — install paths, tools, quality signals, and directory engagement so you can pick the right one for Claude, Cursor, and other MCP clients.
Discovery, exploration, reporting and root cause analysis using all observability data, including metrics, logs, systems, containers, processes, and network connections
Query your Spanlens LLM observability from any MCP client. 7 read tools for request logs, agent traces, cost stats, anomalies, model-savings, and per-user analytics across OpenAI, Anthropic, and Gemini. Open source, self-hostable. npx -y @spanlens/mcp-server
Quality signal
51/100 (Fair)
45/100 (Fair)
Install path
Remote · high
npx · high
Engagement
2 0 0 80,050
0 0 0 11
Tools
Per-second metric collection and visualizationAnomaly detection powered by machine learningSupports metrics, logs, processes, and network connectionsZero-configuration deploymentEfficient resource usage and scalable architectureDistributed monitoring without central data collection
Request logging with full prompt, response, cost, and latency dataAgent tracing for multi-step and tool-based LLM callsCost tracking and model usage analytics across providersAnomaly detection and PII scanningPrompt versioning and A/B experiment supportSelf-hostable with a single Docker command and open source MIT license
