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.
45,870
servers indexed
87
with verified activity
20.0
median score
15,176
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 |
|---|---|---|---|---|---|
| 13651 | io.github.mrfentmen/zenodo-mcp Search research records on Zenodo. No key required. | clean | — | — | 24.0 |
| 13652 | io.github.mrfentmen/zip-codes-mcp Look up US postal codes, cities, and states from Zippopotam. No key required. | clean | — | — | 24.0 |
| 13653 | io.github.mrfentmen/zitadel-mcp MCP server for Zitadel: users, organizations. Works with any instance. | clean | — | — | 24.0 |
| 13654 | io.github.mrfentmen/zork-mcp Use this MCP server to plays classic text adventure games. The LLM is the player, explore, solve... | clean | — | — | 24.0 |
| 13655 | io.github.mrfqcentic/mcp-kokoro-tts Local Kokoro-82M TTS MCP server that synthesizes and plays speech on your machine | clean | — | — | 24.0 |
| 13656 | io.github.mrfqcentic/mcp-notify Minimal MCP server that plays a sound and shows a system banner when an AI agent finishes a task | clean | — | — | 24.0 |
| 13657 | io.github.mrhpython/lens-mcp Outside-in validation gate for AI-generated text; a separate model checks LLM output, fail-closed. | clean | — | — | 24.0 |
| 13658 | io.github.mrkeyoor/should-i-use Honest library picks for coding agents in 25-360 tokens. Tells your agent what NOT to install. | clean | — | — | 24.0 |
| 13659 | JustFill PDF Form Automation Detect, review and fill existing PDF forms from JSON or Excel; reuse saved templates | clean | — | — | 24.0 |
| 13660 | smry Public Reader Read and search exact public source URLs with stable paragraph citations. | clean | — | — | 24.0 |
| 13661 | io.github.mrnh/rigor-mcp Verified statistical inference for AI agents: hypothesis tests, sequential testing, power. | clean | — | — | 24.0 |
| 13662 | io.github.mrocker/linkedin-company-profile LinkedIn companies, hiring signals and public profiles by URL. No login, no cookies. Pay per result. | clean | — | — | 24.0 |
| 13663 | io.github.mrocker/social-data-mcp X, YouTube, TikTok and LinkedIn data plus video transcripts in one stdio MCP server. Pay per result. | clean | — | — | 24.0 |
| 13664 | io.github.mrocker/tiktok-profile-stats TikTok profiles, video stats and transcripts by handle or URL. No login. Pay per result. | clean | — | — | 24.0 |
| 13665 | io.github.mrocker/tiktok-transcripts TikTok video transcripts with timestamps by URL or ID. No login. Charged only per transcript. | clean | — | — | 24.0 |
| 13666 | io.github.mrocker/x-twitter-profile-tweets X (Twitter) profiles and single tweets without login; full timelines with your own cookies. | clean | — | — | 24.0 |
| 13667 | io.github.mrocker/youtube-transcripts YouTube transcripts with timestamps from video links or channels. Charged only per transcript. | clean | — | — | 24.0 |
| 13668 | io.github.mrocker/youtube-video-channel YouTube video metadata, transcripts and channel data by URL or @handle. No API key. Pay per result. | clean | — | — | 24.0 |
| 13669 | io.github.mrosnerr/open-zk-kb Shared, persistent memory for AI assistants, built on the Zettelkasten method. | clean | — | — | 24.0 |
| 13670 | io.github.mrpacstar2-oss/remit Checked language for AI-written agent workflows: limits, cost and data flows known before running. | clean | — | — | 24.0 |
| 13671 | attest — verification for AI agent artifacts Verify an AI agent artifact: schema, emptiness, provenance and mandate authority, Ed25519-signed. | clean | — | — | 24.0 |
| 13672 | drift — mandate enforcement for AI agents Block an action a signed mandate does not permit: amount, payee, audience, currency, window, intent. | clean | — | — | 24.0 |
| 13673 | Xonta Docs RU Russian docs for AI agents: invoices/acts PDF, document parsing, INN checks, medical ad checks | clean | — | — | 24.0 |
| 13674 | io.github.mrsingh86/trimtab-ais US tariff & trade truth: duty actually paid by origin/HS 2017+, HTS rulebook, CBP rulings. No key. | clean | — | — | 24.0 |
| 13675 | YouTube MCP Interact with YouTube data via the official Data API v3 | clean | — | — | 24.0 |
| 13676 | io.github.mrslbt/japan-ux Japanese UI + UX correctness for AI coding agents — typography, forms, keigo, JLReq checks. | clean | — | — | 24.0 |
| 13677 | io.github.mrslbt/nankai-trough Nankai Trough earthquake hazard & building-safety, from official Japan data. No verdicts. | clean | — | — | 24.0 |
| 13678 | io.github.mrslbt/paypay-mcp PayPay QR payments for AI agents: QR codes, status, refunds, cancels. Bilingual JP/EN. | clean | — | — | 24.0 |
| 13679 | io.github.mrslbt/pdf-it Native PDF renderer for AI markdown. Cover, TOC, page-numbered footer. Fonts embedded, zero config. | clean | — | — | 24.0 |
| 13680 | io.github.mrslbt/rakuten-mcp Rakuten Web Service for AI: Ichiba, Books, Travel, Recipe, Kobo, GORA — bilingual, read-only. | clean | — | — | 24.0 |
| 13681 | io.github.mrslbt/rippr-mcp Rip YouTube transcripts to disk for AI agents, RAG pipelines, and LLM workflows. | clean | — | — | 24.0 |
| 13682 | io.github.mrslbt/tabedata-mcp Bilingual JP/EN Japanese food nutrition for AI: 460 sourced konbini, chain & brand items. | clean | — | — | 24.0 |
| 13683 | io.github.mrslbt/xendit-mcp Xendit payment APIs for AI agents. Payment links, payouts, balances, and transactions. | clean | — | — | 24.0 |
| 13684 | Seedance 3.0 Seedance 3.0 info MCP (seedance30.com): product, pricing URL, capabilities. No video gen. | clean | — | — | 24.0 |
| 13685 | JsonFabrica Generate realistic, relational synthetic JSON test data from templates, via the JsonFabrica API. | clean | — | — | 24.0 |
| 13686 | agent-bom Scan AI/MCP dependencies, descriptor injection, risky tool inputs and authentication configuration. | clean | — | — | 24.0 |
| 13687 | io.github.msanchezgrice/agentready Scan any public site for AI-agent visibility; get scored findings, a machine-readable fix pack, and | clean | — | — | 24.0 |
| 13688 | io.github.msanchezgrice/talkform Local Talkform schemas, bundled interview templates, and config validation for AI agents. | clean | — | — | 24.0 |
| 13689 | io.github.msantagiulianab/solana-x402-compliance RFC 9110 x402 Solana compliance screening and micropayments gateway for AI agents. | clean | — | — | 24.0 |
| 13690 | io.github.mscott9160-web/achlens Local-first MCP server and CLI for validating and generating synthetic ACH files. | clean | — | — | 24.0 |
| 13691 | io.github.msdanyg/smart-connections-mcp Local semantic search over Obsidian vaults via Smart Connections embeddings. Multi-vault, private. | clean | — | — | 24.0 |
| 13692 | io.github.msgwing/zerosmtp A free SMTP relay that still takes a username and password, for devices that cannot do OAuth 2.0. | clean | — | — | 24.0 |
| 13693 | Audio MCP Audio perception for AI agents: measure, see, compare, edit and synthesize sound locally. | clean | — | — | 24.0 |
| 13694 | io.github.mshegolev/allure-testops-mcp Allure TestOps MCP — projects, launches, test cases, test results via REST API. | clean | — | — | 24.0 |
| 13695 | Multimeter Scaffold, validate, format, and run YAML .mmt API tests. Do not invent syntax. | clean | — | — | 24.0 |
| 13696 | MMW Managed Memory Workspace Ultra-fast persistent memory workspace with tenant isolation and cross-model continuity. | clean | — | — | 24.0 |
| 13697 | ConnectWise PSA ConnectWise PSA (Manage) MCP server — tickets, time entries, companies, configurations, BYOK | clean | — | — | 24.0 |
| 13698 | IT Glue IT Glue MCP server for MSPs — documents, flexible assets, semantic vector search, RBAC, and BYOK | clean | — | — | 24.0 |
| 13699 | Microsoft Planner Microsoft Planner MCP server — plans, buckets, tasks via Microsoft Graph, ETags handled | clean | — | — | 24.0 |
| 13700 | Grill A second opinion from an unrelated AI model before you commit to a decision. | 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.