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 |
|---|---|---|---|---|---|
| 12651 | io.github.mirzaabubakr/uae-einvoice-mcp UAE e-invoicing MCP: TRN/TIN checks, 51-field PINT AE checklist, UBL XML stubs, mandate timeline. | clean | — | — | 24.0 |
| 12652 | io.github.mischuh/canonic The Open Context Layer for Data Agents | clean | — | — | 24.0 |
| 12653 | Apple Docs 2.0 MCP Apple developer docs, Human Interface Guidelines and 1,700 WWDC sessions with code for AI assistants | clean | — | — | 24.0 |
| 12654 | shotbox Sealed X11/Wayland sessions to see, drive and check real GUI programs: a11y, pictures, sound. | clean | — | — | 24.0 |
| 12655 | io.github.mishrasanjeev/agenticorg Repository MCP adapter for company-scoped workflow candidates and conditional API discovery. | clean | — | — | 24.0 |
| 12656 | io.github.mister-franklin/wetwetwet-legislation Search Belgian & EU legislation: verbatim article text, per-article links, legal Q&A. | clean | — | — | 24.0 |
| 12657 | io.github.misterwigglesworth/easy-notion Markdown-first Notion MCP server. ~6-7x fewer response tokens vs official Notion MCP. 43 tools. | clean | — | — | 24.0 |
| 12658 | AgentWork Outcome Router When your agent is stuck, call route_blocked_outcome for one evidence-backed completion route—free. | clean | — | — | 24.0 |
| 12659 | AgentWork Outcomes Buy a finished outcome through services, agents, marketplaces, humans, tools, or swarms. | clean | — | — | 24.0 |
| 12660 | NullClear Arbiter Autonomous x402 payment schema-escrow arbiter, spend firewall, failover & ERC-8004 Sybil oracle | clean | — | — | 24.0 |
| 12661 | pgvector Similarity search, hybrid search, and index management for pgvector-backed PostgreSQL tables | clean | — | — | 24.0 |
| 12662 | PaperBanana-CN Generate and evaluate academic diagrams and plots with independent model connections. | clean | — | — | 24.0 |
| 12663 | io.github.mizcausevic-dev/mcp-kinetic-gain 75-tool MCP server for 12 Kinetic Gain specs and DefenseTech checks. | clean | — | — | 24.0 |
| 12664 | io.github.mizuki0x/nockchain-mcp Moved to io.github.winter0x/nockchain-mcp. This entry is no longer updated. | clean | — | — | 24.0 |
| 12665 | c3fst Biomedical Search Biomedical search: FDA drugs, MeSH headings, ClinVar genomic variants with BM25 ranking. | clean | — | — | 24.0 |
| 12666 | io.github.mjaskolski/developer-toolkit-mcp The documentation, as a tool your agent can call: 950+ AI-dev guides. Search + fetch tools. | clean | — | — | 24.0 |
| 12667 | io.github.mjaskolski/wondel-skills-mcp Read-only MCP server over 50 book-based agent skills: routes a task to the right framework. | clean | — | — | 24.0 |
| 12668 | io.github.mkXultra/ai-cli-mcp Run Claude, Codex, Gemini, Forge, and OpenCode CLIs through MCP with background jobs | clean | — | — | 24.0 |
| 12669 | 補助金AI Search Japanese subsidies and public company data using J-Grants, gBizINFO, and EDINET. | clean | — | — | 24.0 |
| 12670 | io.github.mkpoli/gmail-mcp Multi-account Gmail on a Cloudflare Worker you deploy yourself: read, send, reply, labels, threads | clean | — | — | 24.0 |
| 12671 | io.github.mkrupkin/rixot-mcp Let AI agents buy dofollow backlinks: search 50,000+ vetted sites, order, publish. 7 hosted tools. | clean | — | — | 24.0 |
| 12672 | io.github.mlartab/agentwebintel Proxy-rotated web scraping and cross-platform intelligence for AI agents. | clean | — | — | 24.0 |
| 12673 | Agent Ready Scan any URL for AI agent readability — Vercel Spec, llmstxt.org, and agent-protocol manifests. | clean | — | — | 24.0 |
| 12674 | Scholar Sidekick Catch AI-fabricated citations (real DOI + fake title). Retraction, open-access, 10,000+ CSL styles. | clean | — | — | 24.0 |
| 12675 | io.github.mlawsonking/agent-firewall-mcp Input/output safety for AI agents: known-pattern injection and obfuscation scan, URL/IP, secrets. | clean | — | — | 24.0 |
| 12676 | io.github.mlawsonking/agent-guards All six agent guard suites in one local MCP server, with optional cloud intelligence. | clean | — | — | 24.0 |
| 12677 | io.github.mlawsonking/code-guard-mcp Security scan for AI-generated code: injection, SSRF, secrets, weak crypto, unsafe deserialization. | clean | — | — | 24.0 |
| 12678 | io.github.mlawsonking/email-guard-mcp Email safety for AI agents: scan inbound for prompt-injection/phishing + outbound for secret leaks. | clean | — | — | 24.0 |
| 12679 | io.github.mlawsonking/package-guard-mcp Supply-chain guard for AI coding agents: verify packages, check vulns/malware, detect typosquats. | clean | — | — | 24.0 |
| 12680 | io.github.mlawsonking/payment-guard-mcp Pre-send risk check for AI agents that move money — screen an address or payment URL before sending. | clean | — | — | 24.0 |
| 12681 | io.github.mlawsonking/web-tools-mcp 10 no-LLM web tools: URL to Markdown, metadata, JSON-LD, MX, scrape, RSS, DNS, RDAP, SSL, HTTP. | clean | — | — | 24.0 |
| 12682 | PyScrappy Web-scraping toolkit with 22 tools for structured web data as JSON for AI agents. | clean | — | — | 24.0 |
| 12683 | io.github.mleoca/ucn Auditable, conserved AST code intelligence for AI agents. JS/TS, Python, Go, Rust, Java, C/C++, C#. | clean | — | — | 24.0 |
| 12684 | Mlola UI Mlola UI components, tokens and design rules for coding agents, with a markup checker | clean | — | — | 24.0 |
| 12685 | PDF Modifier Modify PDF text, replace with regex, and analyze layout while preserving fonts. | clean | — | — | 24.0 |
| 12686 | MsgPack (LsMsgPack) Decodes MsgPack (LsMsgPack schemas, type ids) as text and reads it from variables while debugging. | clean | — | — | 24.0 |
| 12687 | io.github.mlugo-apx/detectzestack-mcp Detect any website's tech stack, security headers, SSL, DNS and CVEs via DetectZeStack. | clean | — | — | 24.0 |
| 12688 | Enterprise Architect Read-only search and navigation of Sparx Enterprise Architect .qea model exports | clean | — | — | 24.0 |
| 12689 | io.github.mmahdiahamed92-png/autonomous-intelligence Non-custodial, rug-gated crypto swaps + token safety + discovery for AI agents. | clean | — | — | 24.0 |
| 12690 | 华哥·全国招投标数据 查询 hndcw.com 全国政府招投标 / 建设项目库，可按关键词、省份、城市、行业、预算区间筛选，返回项目标题、地区、预算(万元)、业主单位、阶段、公告日期与原文链接。 | clean | — | — | 24.0 |
| 12691 | 华哥·社会调查服务 社会调查与现场执行服务咨询：满意度 / 民意 / 舆情 / 暗访 / 面访 / 座谈会等服务能力与报价查询，对接 hndcw.com 服务预约。 | clean | — | — | 24.0 |
| 12692 | 华哥·海南政策法规 检索海南本地政策法规与惠企政策库，覆盖营商环境、民生、政府采购、产业扶持等主题，返回政策标题、发布机关、发布日期与原文链接。 | clean | — | — | 24.0 |
| 12693 | 华哥·鸣儿招投标问答 「鸣儿」招投标智能助手：回答投标流程、资质要求、找项目、政策匹配等提问，并可联动项目库返回匹配标讯。 | clean | — | — | 24.0 |
| 12694 | Favro Favro cards, boards and collections over MCP: read, search, write, and resolve names to ids. | clean | — | — | 24.0 |
| 12695 | io.github.mmedum/gitlab-mcp GitLab over MCP from your own account: issues, merge requests, reviews, the repository and CI. | clean | — | — | 24.0 |
| 12696 | io.github.mmedum/google-calendar-mcp Google Calendar over MCP: calendars, events, recurrence and availability. | clean | — | — | 24.0 |
| 12697 | io.github.mmedum/google-chat-mcp Google Chat as MCP tools: read, search and write to your spaces, direct messages and sidebar. | clean | — | — | 24.0 |
| 12698 | io.github.mmedum/google-docs-mcp Google Docs as MCP tools: read, edit, suggest and comment on documents. | clean | — | — | 24.0 |
| 12699 | Google Drive Google Drive at the file boundary: find, organize, share, transfer and follow what changed. | clean | — | — | 24.0 |
| 12700 | io.github.mmedum/google-mail-mcp Gmail over MCP from your own account: search, read threads and messages, labels and drafts. | 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.