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 |
|---|---|---|---|---|---|
| 21351 | Discord Discord for LLM agents: 168 tools for messages, moderation, channels, roles, threads and AutoMod. | clean | — | — | 24.0 |
| 21352 | ContextLib A project's long-term memory as plain Markdown files, with an append-only, tamper-evident log. | clean | — | — | 24.0 |
| 21353 | AgentBrain Handoffs Exact, durable handoffs between AI coding agents: one turn in the right session, never twice. | clean | — | — | 24.0 |
| 21354 | Tanpin Item-by-item inventory that reorders itself: per-SKU forecasts, purchase orders and ETAs. | clean | — | — | 24.0 |
| 21355 | Remove AI Watermarks Identify and remove AI watermarks and provenance metadata from your own images and video. | clean | — | — | 24.0 |
| 21356 | io.github.wilzer/aidelly Agent-operated social media for agencies — www.aidelly.ai. Post, approve, analyze on 11 networks. | clean | — | — | 24.0 |
| 21357 | io.github.winds3753/landbenchmark-mcp Satellite land due-diligence: a green/caution/walk-away verdict with cited signals for any parcel. | clean | — | — | 24.0 |
| 21358 | WingFoil WingFoil — the repo-native intent layer for AI-native software engineering | clean | — | — | 24.0 |
| 21359 | io.github.winter0x/lighter-mcp Read Lighter perpetual markets and place guarded orders, including the H100 compute-price market. | clean | — | — | 24.0 |
| 21360 | io.github.winter0x/nockchain-mcp Community-built read-only Nockchain access: balances, payment verification, blocks, node health. | clean | — | — | 24.0 |
| 21361 | io.github.wiresage/mikrotik-mcp MCP server for MikroTik routers: firewall, NAT, routing, DHCP, DNS, WireGuard and more via SSH. | clean | — | — | 24.0 |
| 21362 | LoopSkill Search, install and compose AI agent skills, loops and bundles from the LoopSkill marketplace. | clean | — | — | 24.0 |
| 21363 | AION SUPREME Agent Temple Verified agent routing with bounded discovery, outcome evidence and economic policy. | clean | — | — | 24.0 |
| 21364 | io.github.wismhero-maker/scrupp Export LinkedIn, Sales Navigator and Apollo searches; find decision makers and verified work emails | clean | — | — | 24.0 |
| 21365 | WITAN Markets Search can't find it; agents buy it here: measured numbers and data its sellers hold the rights to. | clean | — | — | 24.0 |
| 21366 | 402xAgent Check an x402 endpoint before your agent pays: pay, skip or recheck. Plus a verified x402 catalog. | clean | — | — | 24.0 |
| 21367 | io.github.withpica/pica manage your music catalog through conversation — works, recordings, credits, agreements, royalties | clean | — | — | 24.0 |
| 21368 | writ Commit-time policy checks for AI agent writes (ALLOW/DENY/STEP_UP) with a tamper-evident audit log. | clean | — | — | 24.0 |
| 21369 | io.github.wizard-exe/stoxly Free stock, ETF & crypto analysis: 10-point score, verdict and key metrics for any ticker. | clean | — | — | 24.0 |
| 21370 | io.github.wjabanjj/aifp-mcp Persistent memory MCP server for AI coding assistants. Chinese-first and fully local. | medium | — | — | 24.0 |
| 21371 | io.github.wkoverfield/plzebo Cost-parity bench for agent loops: $/success and time across model mixes, with verifiable receipts. | clean | — | — | 24.0 |
| 21372 | io.github.wkoverfield/quilt Track which AI agent wrote which lines in a shared Git checkout; each commits only its own lines. | clean | — | — | 24.0 |
| 21373 | io.github.wkoverfield/switchboard One firewall and password manager for all your AI coding agents' MCP servers and secrets. | clean | — | — | 24.0 |
| 21374 | Ontology Atlas Read and write one codebase ontology kept as Markdown in the repository. | clean | — | — | 24.0 |
| 21375 | Boardsesh Climbing Logbook Read-only access to your Boardsesh logbook across Kilter, Tension, MoonBoard and more | clean | — | — | 24.0 |
| 21376 | Kilter Board Logbook Read-only access to your Kilter Board logbook: sessions, sends, projects and grade stats | clean | — | — | 24.0 |
| 21377 | MUJ428 Trust Layer — Bind Approved Intent to Verified Effect Payment-rail-independent intent-to-effect integrity for consequential agent actions. | clean | — | — | 24.0 |
| 21378 | MUJ428 Trust Layer — VERIFY BEFORE ACT MUJ428 verifies intent and evidence before consequential AI-agent actions. | clean | — | — | 24.0 |
| 21379 | OneQAZ Trading Intelligence Verifiable crypto/KR/US market intelligence for AI agents: signals, hash-chained ledger. Not advice. | clean | — | — | 24.0 |
| 21380 | io.github.woladi/macos-vision-mcp Local OCR & screen understanding for agents: read any window, find what to click. No uploads. | clean | — | — | 24.0 |
| 21381 | io.github.woladi/pseudonym-mcp Locally pseudonymizes sensitive text before cloud LLM work and restores the tokens afterward. | clean | — | — | 24.0 |
| 21382 | Desktop Commander MCP server for terminal commands, file operations, and process management | medium | — | — | 24.0 |
| 21383 | MessNoMore Data Tools Visa sponsors, school holidays, halal, HS codes, baggage, IAB categories, mobile plans, recipes. | clean | — | — | 24.0 |
| 21384 | SearchHub Aggregate Serper, Tavily, Exa and AnySearch behind one MCP-ready API with key rotation and quotas. | clean | — | — | 24.0 |
| 21385 | Monumenten Look up Dutch BAG verblijfsobject IDs and monumental status. | clean | — | — | 24.0 |
| 21386 | io.github.woonyong-choi/hermes-agent-mcp Operate a local Hermes Agent install over stdio: tasks, cron, config, gateway, doctor. No network. | clean | — | — | 24.0 |
| 21387 | io.github.woowoeth/ourword Search Chinese deep-reads of 190+ podcasts; every point and quote has an audio timestamp. | clean | — | — | 24.0 |
| 21388 | io.github.worakorn-prince/th-memory-mcp Local long-term memory MCP server (SQLite) for AI coding agents — OpenCode, Claude Code, Cursor | clean | — | — | 24.0 |
| 21389 | Pullzip Inspect, search and safely extract zip/7z/rar/tar archives; repair garbled CJK file names. | clean | — | — | 24.0 |
| 21390 | Figma Vector MCP Let Claude create and edit fully editable vector nodes on the Figma canvas. | clean | — | — | 24.0 |
| 21391 | io.github.worklore/worklore Search worklore stories and x-ray any skill or story capability tier (T0-T4) before you run it. | clean | — | — | 24.0 |
| 21392 | Woven Make and edit videos in Woven, the AI video editor for Mac. Needs the Woven app. | clean | — | — | 24.0 |
| 21393 | Reaper Daemon REAPER MCP server: let Claude read your session, set FX, write automation and measure mix moves. | clean | — | — | 24.0 |
| 21394 | Mountable Persistent filesystem for AI agents. Its files survive even when the sandbox is gone. | clean | — | — | 24.0 |
| 21395 | Holographic Memory Local persistent memory for AI agents with recall, search, forgetting, and encrypted storage. | clean | — | — | 24.0 |
| 21396 | Dispatch The shared task board for coding agents: claim tasks, comment, message agents, save memory. | clean | — | — | 24.0 |
| 21397 | Ableton Live MCP Server Control Ableton Live with 156 typed tools for music production and offline .als analysis. | clean | — | — | 24.0 |
| 21398 | ScreenSeal Sanctions screening for AI agents: check a name against OFAC and EU lists. Free during launch. | clean | — | — | 24.0 |
| 21399 | AEM Content Manager (ACM) Validate and run Groovy scripts on Adobe Experience Manager through AEM Content Manager (ACM). | clean | — | — | 24.0 |
| 21400 | io.github.wtznicy/my-websearch MyWebSearch - multi-engine web search MCP server, CLI and local daemon. No API keys required. | 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.