Updated weekly · Free & open
Which MCP servers are actually maintained?
The official registry lists every Model Context Protocol server but tells you nothing about whether any of them is still alive. This index scores each one on maintenance activity, flags what deserves a second look before you install it, and shows exactly how every number was reached.
41,986
servers indexed
88
with verified activity
21.0
median score
13,104
carrying risk flags
last refreshed
The weekly report
What moved, what dropped, and what appeared — a short read every Monday. No spam, unsubscribe in one click.
Leaderboard
Activity & maintenance, not security — how this is scored| # | Server | Flags | Stars | Change | Score |
|---|---|---|---|---|---|
| 351 | OpenMayhem Use OpenMayhem text, embedding and media models with explicit cost controls. | clean | — | — | 24.0 |
| 352 | OpenSwitchboard Your AI posts what you want or have. You are introduced anonymously to whoever has the other half. | clean | — | — | 24.0 |
| 353 | OrangePro Find test gaps, generate grounded tests, and dynamically prove behavior with mutation testing. | clean | — | — | 24.0 |
| 354 | Nimrod Web search with quality scores; web pages are read on your computer by the local server. | clean | — | — | 24.0 |
| 355 | ZeroMind (OrigoZero game engine) Build, run and publish 3D games in the Zero engine from Claude Code, Cursor or Codex, over MCP. | clean | — | — | 24.0 |
| 356 | ai.outfitmaker/outfit-assistant Your own closet in your AI: outfits from clothes you own, rendered on a model inline. | clean | — | — | 24.0 |
| 357 | Overwing Guardrails for LLM output: pass / fail / review verdicts and one recommended action. Hosted or npm. | clean | — | — | 24.0 |
| 358 | ai.papyruslabs/seshat-mcp Structural code intelligence for AI agents: real call graphs, blast radius, and change history. | clean | — | — | 24.0 |
| 359 | Liminal Augment your work with Liminal. Stop repeating yourself and build on what’s already solved. | clean | — | — | 24.0 |
| 360 | ai.pictomancer/image-processing Image processing for AI agents: resize, convert, compress, crop, and web-ready AI-generated images. | clean | — | — | 24.0 |
| 361 | PigeonRelay Delegate tasks between AI agents on different platforms and collect the results. | clean | — | — | 24.0 |
| 362 | PixelDojo Generate images, video, audio and short films with 140+ AI models from any MCP client. | clean | — | — | 24.0 |
| 363 | PlayDrop Publish, test and share browser games on PlayDrop from your AI agent. | clean | — | — | 24.0 |
| 364 | PLCs.ai Query Allen-Bradley and Siemens PLC projects, live tag values, and analyses in plain English. | clean | — | — | 24.0 |
| 365 | ai.plori/plori Plori runs AI agents in Workspaces. | clean | — | — | 24.0 |
| 366 | Popdot AI Rent verified subdomains by the hour, day, or month. Free 24h trials, x402 USDC on Base. | clean | — | — | 24.0 |
| 367 | PCD (Portable Context Deck) Your portable context layer — load it into any AI. | clean | — | — | 24.0 |
| 368 | Positif The agent switchboard: identity, policy, loop-guard, and an append-only audit ledger. | clean | — | — | 24.0 |
| 369 | ai.posteverywhere/mcp The agentic social media scheduler. Write, schedule and publish to all top social platforms. | clean | — | — | 24.0 |
| 370 | Postfleet Give an AI agent its own email address: send, reply, read, and wait for mail. | clean | — | — | 24.0 |
| 371 | Povver — Strength Training Your strength-training data for any AI assistant: workouts, progress, muscle volume, routines. | clean | — | — | 24.0 |
| 372 | ai.primateintelligence/mcp Video scene understanding for AI agents via the Primate Vision API. | clean | — | — | 24.0 |
| 373 | ReasonGraph Cloud memory Graph memory for AI agents: entities, cause-effect links, cross-session recall, time travel. | clean | — | — | 24.0 |
| 374 | ProductNow Connect AI agents to ProductNow's context engine to search, create, review, and act. | clean | — | — | 24.0 |
| 375 | PDS Project AI MPP Connector Read, analyze, and safely edit Microsoft Project MPP files. | clean | — | — | 24.0 |
| 376 | ai.proxyllm/proxyllm-mcp OpenAI-compatible LLM gateway: models, savings math, key provisioning, autonomous email-OTP signup | clean | — | — | 24.0 |
| 377 | PubFi MCP Use MCP 2026-07-28 discovery or 2025-11-25 initialize to list and execute PubFi routes. | clean | — | — | 24.0 |
| 378 | ai.pullpush/pullpush-mcp Connect any two APIs and keep them in sync — 48 MCP tools with shadow previews and diagnostics. | clean | — | — | 24.0 |
| 379 | QCDatabase.AI Connects AI assistants to QCDatabase.AI for everyday construction quality-control work. | clean | — | — | 24.0 |
| 380 | Qlane AI QA that runs your app in a browser on every pull request: projects, test targets, test cases. | clean | — | — | 24.0 |
| 381 | Norma by Quality Clouds Checks AI-written code against your rules as it is written, and keeps a record of what it found. | clean | — | — | 24.0 |
| 382 | QuillHub Meeting transcripts for AI agents: search calls, read who said what, transcribe files and links. | clean | — | — | 24.0 |
| 383 | Quillm Dashboards, trackers and docs your agents build and keep current. Your team reads them by link. | clean | — | — | 24.0 |
| 384 | ai.radmail/radmail-mcp Email OS for agents - real-inbox search, triage, commitments, and a verifiable BEC hard-stop. | clean | — | — | 24.0 |
| 385 | ai.ragjur/mcp Brazilian legal search and jurimetria: 115M+ court decisions from 90+ courts across 14 MCP tools. | clean | — | — | 24.0 |
| 386 | Raven Design intelligence for coding agents: audits, design systems, and a taste profile agents consult. | medium | — | — | 24.0 |
| 387 | RCLL Self-hosted shared memory for a team of AI agents. Rooms, L0-L3 depth, no LLM on the read path. | clean | — | — | 24.0 |
| 388 | Rechtssysteem.ai Lekkage-vrije voorspelling van Nederlandse rechtszaken, getraind op 609.715 uitspraken | clean | — | — | 24.0 |
| 389 | refd Read AI search visibility, competitors, and citations from refd; manage tracked prompts. | clean | — | — | 24.0 |
| 390 | Regulations.ai — Global AI Law Tracker AI laws from 110+ countries, enforcement actions and a 3,900-term glossary. Free, no API key. | clean | — | — | 24.0 |
| 391 | Revelara Reliability intelligence: production incidents, risk register, controls catalog, knowledge graph. | clean | — | — | 24.0 |
| 392 | RightCard Which of your credit cards to use at any store, from verified bank data. No bank login. | clean | — | — | 24.0 |
| 393 | Rillsoft Project MCP server built into Rillsoft Project 10 for multi-project resource planning (local, Windows) | clean | — | — | 24.0 |
| 394 | RiskState — Crypto Risk Engine Live BTC/ETH risk state: risk policy, market structure and trading playbooks. Keyless free tier. | clean | — | — | 24.0 |
| 395 | Rithmo AI agent governance with resolved business context, current decisions, provenance, and supersession. | clean | — | — | 24.0 |
| 396 | Rivalize Competitive intelligence for agents: competitor teardowns, pricing, ads, reviews and momentum. | clean | — | — | 24.0 |
| 397 | RoboSystems Accounting knowledge graphs: SEC XBRL filings, QuickBooks ledgers, reports and forecasts over MCP. | clean | — | — | 24.0 |
| 398 | xbrlkit Read SEC EDGAR and XBRL filings with an AI: 18 tools over the filing itself. Local, free, no account | clean | — | — | 24.0 |
| 399 | RoboWrite Hosted RoboWrite MCP server: recover briefs and drafts, run the reviewed URL-to-Markdown workflow. | clean | — | — | 24.0 |
| 400 | RocketList Search current startup jobs and hiring companies through RocketList's public read-only data. | clean | — | — | 24.0 |
A score measures maintenance activity, not safety. A high score does not mean a server is secure, and a low one does not mean it is dangerous — see the methodology for what each signal does and does not tell you.