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.
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
AI API cost tracking and budget enforcement across 11 LLM providers. 6 tools for spend analytics, budget monitoring, session summaries, and key management.
Quality signal
45/100 (Fair)
45/100 (Fair)
Install path
npx · high
npx · high
Engagement
0 0 0 11
1 0 0 16
Tools
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
Proxy API gateway logging requests with token counts and dollar costsBudget enforcement rejecting requests exceeding limits before provider callSDK support for Python and TypeScript with local cost estimation optionCLI tool wrapping commands to intercept and report costs without code changesIntegration handlers for LangChain, LlamaIndex, and Pydantic AIGitHub Action for CI cost capping and PR comment reporting
