io.github.mims-harvard/tooluniverse
2,500+ scientific tools for AI scientists: life science, research, literature, and more.
MCP servers for AI memory, vector search, model APIs, and LLM tooling - scored on security and token efficiency.
MCPpedia tracks 8,171 ai / ml MCP servers. 2,340 of them score at least 50 out of 100, and 1,157 clear 70 - about 14% of what has been published in this space. The remaining 5,831 are thinner: registry entries with no description, no published tool schema, or no commit in the last year. They are all still listed here, because knowing a server exists and is unmaintained is worth as much as knowing a good one exists.
io.github.mims-harvard/tooluniverse leads the list at 96/100. Gemini CLI (95) and Codebase Memory MCP (95) follow. Every score is the same five weighted inputs: security (CVE scanning, tool-poisoning detection, and whether the server authenticates at all), maintenance (commit recency, release cadence, and download trend), documentation, client compatibility, and token efficiency - how much of your context window the tool definitions consume before you have asked anything.
37 of these servers are published by the vendor behind the underlying API rather than by a third party, which is usually the difference between an integration that tracks upstream changes and one that quietly stops working. 15 currently carry an open CVE; those are flagged on the server's own page with the advisory and its severity.
Also see: All AI / ML servers, Best Productivity, Best Developer Tools, Best Data, Best Finance
Last updated
2,500+ scientific tools for AI scientists: life science, research, literature, and more.
An open-source AI agent that brings the power of Gemini directly into your terminal.
Codebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens.
Read-only access to 71 Suede skills: discovery, install options, SEO audits, A-F grading.
Connect Claude to any OpenAI-compatible LLM endpoint and offload routine work to a local model.
Fastest enterprise AI gateway (50x faster than LiteLLM) with adaptive load balancer, cluster mode, guardrails, 1000+ models support & <100 µs overhead at 5k RPS.
MCP server for mobile app automation: verify, control, and debug iOS, Android, TV, and desktop apps
The official MCP server implementation for the Perplexity API Platform
🧠 An adaptation of the MCP Sequential Thinking Server to guide tool usage. This server provides recommendations for which MCP tools would be most effective at each stage.
Unified real-time search engine skill for AI agents.