10,247 servers in this category
MCPpedia tracks 10,346 ai / ml MCP servers. 3,082 of them score at least 50 out of 100, and 1,619 clear 70 - about 16% of what has been published in this space. The remaining 7,264 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.callstack/agent-device leads the list at 96/100. io.github.HUANGCHIHHUNGLeo/claude-real-video (96) and Modelcontextprotocol (96) 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. 19 currently carry an open CVE; those are flagged on the server's own page with the advisory and its severity.
Also see: Best AI / ML MCP servers, Productivity, Developer Tools, Data, Finance
Last updated
MCP server for mobile app automation: verify, control, and debug iOS, Android, TV, and desktop apps
Let any LLM watch a video locally — and search everything it has ever watched.
The official MCP server implementation for the Perplexity API Platform
2,700+ 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.
AgentRQ: Human-in-loop realtime conversational task manager for AI Agents.
A cross-platform desktop application for managing AI Agents and MCP Servers. 一款用于管理AI智能体与MCP服务器的跨平台桌面应用程序。
Give Claude the ability to watch and understand videos — Claude Code plugin with frame extraction and multimodal audio analysis
Read-only access to 71 Suede skills: discovery, install options, SEO audits, A-F grading.
Codebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens.
Fastest enterprise AI gateway (50x faster than LiteLLM) with adaptive load balancer, cluster mode, guardrails, 1000+ models support & <100 µs overhead at 5k RPS.
Full Agent Swarm API and MCP server with local SQLite storage for multi-agent orchestration.
DeepSeek Harness (DSH) backup & restore plugin — export, import, migrate and sync your complete DSH configuration, plugins, MCP servers, skills and workspace. One-click migration to another machine.
Memory for AI agents that learns what is wrong and stops repeating it. Mark a memory wrong and it stops coming back; newer facts replace old ones. Local SQLite store and MCP server, persistent across sessions; hippo init wires it into Claude Code, Codex, Cursor, OpenClaw, OpenCode and Pi. Zero runtime deps, MIT, opt-in hosted TypeSafe Jev reranker.
Author, generate, validate and govern AI agent rules, skills, plugins and MCP configuration across 52 coding assistants. Review with verified model evidence, evaluate skills, lock and sign dependencies, and publish bundles. CLI, MCP server and Go API.
Web search, deep research, prediction markets & crypto data for AI agents. Pay per call via x402.
Local-first AI memory with knowledge graphs and hybrid search. 17+ AI tools via MCP. Free.
Context engineering for AI agents. ~80% fewer tokens. Fix tool overload. Skills and memory with in-process BM25 retrieval. No vector DB. No embeddings.
AI-powered VMware vCenter/ESXi VM lifecycle and deployment with 61 MCP tools.
Generate game sprites and assets from text prompts for game development.