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.
49,991
servers indexed
87
with verified activity
20.0
median score
17,377
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 |
|---|---|---|---|---|---|
| 21501 | TeamShared Shared memory for coding agents. Stop re-explaining your codebase every session. | clean | — | — | 24.0 |
| 21502 | io.github.xhighhongo41/patent-checker Prior-art exploration for software projects; finds related patents, never judges infringement | clean | — | — | 24.0 |
| 21503 | io.github.xianguoGou/h5-devtools-mcp Debug H5 pages inside Android app WebViews: console logs, exceptions, run JS. | clean | — | — | 24.0 |
| 21504 | io.github.xiaoba-dev/atlaxy Search 500+ AI products, models, agents and orgs with explainable scores. Read-only MCP for Atlaxy. | clean | — | — | 24.0 |
| 21505 | EveryInfra Structured data from 90 platforms (RedNote, Douyin, TikTok, Amazon), web search, CAPTCHA solving. | clean | — | — | 24.0 |
| 21506 | NovelAI Image MCP NovelAI image generation as MCP tools: txt2img, img2img, inpaint, upscale, Director, ControlNet. | clean | — | — | 24.0 |
| 21507 | io.github.xixi048/create-all-cg-save Byte-patch CG unlock flags in offline single-player game saves, with backup and rollback. | clean | — | — | 24.0 |
| 21508 | io.github.xixi048/publish-to-all-skill-stores List, check and package a SKILL.md skill for every agent-skill store. | clean | — | — | 24.0 |
| 21509 | ReceiptRail Read-only on-chain receipt check for x402 payments; confirm settlement before trusting a tx. | clean | — | — | 24.0 |
| 21510 | io.github.xkqg/matplotlibnet Renders MatPlotLibNet charts to PNG, SVG or PDF from a JSON spec an AI agent writes. | clean | — | — | 24.0 |
| 21511 | SSH Host Storage & Remote Exec Stdio MCP server for SSH host storage and remote command execution with a connection-pool monitor. | clean | — | — | 24.0 |
| 21512 | DeepSeek Visionary DeepSeek web vision model as an MCP server with browser auto-login. | clean | — | — | 24.0 |
| 21513 | Ba-Zi.ai Chinese Astrology BaZi Four Pillars charts, bone weight fortune (称骨) and Chinese almanac (黄历) by Ba-Zi.ai. | clean | — | — | 24.0 |
| 21514 | io.github.xmpuspus/cloudwright Cloud architecture and migration planning with costs, controls, evidence, and deployable IaC. | clean | — | — | 24.0 |
| 21515 | PH Civic Data PH civic data as MCP tools: the full PSA OpenSTAT catalog, hazards, procurement. 41 tools. | clean | — | — | 24.0 |
| 21516 | Academic Research Kernel Deterministic research state, evidence validation and statistical recomputation. | clean | — | — | 24.0 |
| 21517 | io.github.xnjiang/37soul-mcp Run your 37Soul AI characters from any MCP client: list them, chat with them, and tell them to post. | clean | — | -62.0 | 24.0 |
| 21518 | io.github.xnjiang/autowhisper-mcp Drive your AutoWhisper AI CMO to generate and publish marketing content from any MCP client. | clean | — | — | 24.0 |
| 21519 | io.github.xona-labs/xpay Xona Wallet: agent wallet for AI agents. x402 payments, AgenC hires, 20k+ services | clean | — | — | 24.0 |
| 21520 | Cisco Modeling Labs CML An MCP server that provides access to common Cisco Modeling Labs (CML) operations. | clean | — | — | 24.0 |
| 21521 | GXEON Agent Marketplace GXEON services, prepaid packs from R$0.99, purchase planning, and agent buyer guidance. | clean | — | — | 24.0 |
| 21522 | io.github.xpex-systems-ai/xpex-plugin-factory MCP plugin factory and x402 Agent Kit API for external agents, at 0.01 USDC per call. | clean | — | — | 24.0 |
| 21523 | io.github.xplainable/xplainable-mcp-server Train, explain, optimise and deploy transparent glass-box ML models via workflow tools. | clean | — | — | 24.0 |
| 21524 | io.github.xplormityai/searchdock-cli Read-only Google Search Console analytics, URL inspection and sitemaps via SearchDock CLI. | clean | — | — | 24.0 |
| 21525 | Awaitless Durable execution and named concurrency queues for coding agents across local, SSH, and Slurm. | clean | — | — | 24.0 |
| 21526 | io.github.xsf0221/pattern-vista End-of-day US equity data: MA200 deviation rankings, market breadth, chart-pattern win rates. | clean | — | — | 24.0 |
| 21527 | Playwright E2E MCP Diagnose and fix failing Playwright tests: traces, verified fixes, flaky/order verdicts, a11y audit. | clean | — | — | 24.0 |
| 21528 | io.github.xsronhou/scrapio-mcp Fetch, crawl, and search the web: Google, Amazon, Walmart, Booking.com, Agoda, and YouTube data. | clean | — | — | 24.0 |
| 21529 | XTELL Serial Serial terminal with a GUI that AI assistants drive over MCP: read device logs, send commands. | clean | — | — | 24.0 |
| 21530 | io.github.xtrustinfo/company-lookup Ukrainian business directory: companies, contacts and registry details (xtrust.info). | clean | — | — | 24.0 |
| 21531 | io.github.xxxoooxoxo/wiff Deterministic, resumable multi-agent workflows across Codex, Claude, Cursor, and Kimi. | clean | — | — | 24.0 |
| 21532 | ocular Vision tools for coding agents: screenshots, OCR, UI diffs, errors, tables, and charts. | clean | — | — | 24.0 |
| 21533 | Verbatim Transcribe 让 agent 驱动本机的 Verbatim 音视频转写与博主观点分析：提交转写、轮询、搜索转写库。 | clean | — | — | 24.0 |
| 21534 | tc39-mcp Independent MCP server for the TC39 specs (ECMA-262 + ECMA-402): clauses, search, diffs, history. | clean | — | — | 24.0 |
| 21535 | YRUZ x402 tools Pay-per-call agent tools, x402 v1+v2, USDC Base/Solana: audit, extract, enrich, URL safety, crypto | clean | — | — | 24.0 |
| 21536 | io.github.yBookoff/thebrain MCP server for TheBrain 15: search by meaning, graph traversal and batch writes over the local API | clean | — | — | 24.0 |
| 21537 | Afrotech.guide Search and plan AfroTech 2026 events, sessions, people, companies, food, and member itineraries. | clean | — | — | 24.0 |
| 21538 | ReClip Inspect and download authorized media or precise clips locally with yt-dlp. | clean | — | — | 24.0 |
| 21539 | FrankenSurf Read any web page and search the web: 28 tools, cheapest first, every page checked. | clean | — | — | 24.0 |
| 21540 | Repomix Pack local or remote codebases into AI-friendly files that LLMs and coding agents can read or search | clean | — | — | 24.0 |
| 21541 | io.github.yamantaka520/agent-memory-os Local-first memory engine for AI-agent teams: team/project ACL, recall, and federated sync. | clean | — | — | 24.0 |
| 21542 | io.github.yaminbkk/nexusmem Local-first memory for AI coding agents: shell history with exit codes, git diffs, docs, MCP. | clean | — | — | 24.0 |
| 21543 | PaletteGet Curated app, web and mini program color palettes with WCAG contrast and CSS variables. | clean | — | — | 24.0 |
| 21544 | Memory Bridge (忆桥) Evidence-cited knowledge base for internal documents: audit trail, versioning, namespace isolation. | clean | — | — | 24.0 |
| 21545 | Overleaf Overleaf MCP server for Claude, Codex, ChatGPT, and Cursor with safe LaTeX editing and review. | clean | — | — | 24.0 |
| 21546 | TopicForge Read-only MCP server for ROS2 and DDS: topics, participants, QoS mismatches, bags. | clean | — | — | 24.0 |
| 21547 | Base Token Facts Base token checks for agents: simulated buy and sell, taxes, honeypots. Pay per call in USDC (x402). | clean | — | — | 24.0 |
| 21548 | Inspectrum Review coding-agent plans on demand with peer models, attributed findings, and a structured verdict. | clean | — | — | 24.0 |
| 21549 | io.github.yantrikos/yantrikdb-mcp Cognitive memory for AI agents — semantic recall, knowledge graph, and contradiction detection | clean | — | — | 24.0 |
| 21550 | io.github.yaotsakpo/ledgerfc Grounded sports predictions plus European soccer and tennis arbitrage data for AI agents. | 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.