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.
MCP-native agent evaluation and observability server with trace logging, output quality evaluation, cost tracking, 12 built-in eval rules, real-time dashboard, and PII detection.
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
48/100 (Fair)
45/100 (Fair)
Install path
npx · high
npx · high
Engagement
0 0 0 7
0 0 0 11
Tools
Hierarchical span trace logging with latency, token usage, and cost13 built-in evaluation rules including PII and prompt injection detectionCost aggregation and budget threshold alertsReal-time dark-mode web dashboard for trace and evaluation visualizationSQLite storage for instant querying of trace dataCustom evaluation rules via Zod schemas
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
