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.
54,385
servers indexed
86
with verified activity
20.0
median score
19,556
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 |
|---|---|---|---|---|---|
| 43101 | Spain Payments (Stripe — cards / Apple Pay) Spain payments for AI agents — cards / Apple Pay via Stripe. Never holds funds. | clean | — | -0.6 | 14.3 |
| 43102 | Sweden Payments (Stripe — Klarna) Sweden payments for AI agents — Klarna via Stripe. Never holds funds. | clean | — | -0.6 | 14.3 |
| 43103 | Switzerland Payments (Stripe — TWINT) Switzerland payments for AI agents — TWINT via Stripe. Never holds funds. | clean | — | -0.6 | 14.3 |
| 43104 | Taiwan Payments & E-Invoice (ECPay 綠界 / NewebPay 藍新) Taiwan payments (ECPay 綠界 + NewebPay 藍新) & e-invoices for AI agents. Stateless, never holds funds. | clean | — | -0.6 | 14.3 |
| 43105 | Tanzania Payments (Flutterwave — M-Pesa / Tigo Pesa) Tanzania payments for AI agents — M-Pesa / Tigo Pesa via Flutterwave. Never holds funds. | clean | — | -0.6 | 14.3 |
| 43106 | Thailand Payments (Opn/Omise — PromptPay QR / cards / TrueMoney) Thailand payments for AI agents — PromptPay QR, cards, TrueMoney via Opn (Omise). Never holds funds. | clean | — | -0.6 | 14.3 |
| 43107 | Turkey Payments (iyzico — Turkish cards / taksit) Turkey payments for AI agents — Turkish cards / taksit via iyzico. Never holds funds. | clean | — | -0.6 | 14.3 |
| 43108 | United Arab Emirates Payments (Tap Payments — Apple Pay / cards) United Arab Emirates payments for AI agents — Apple Pay / cards via Tap Payments. Never holds funds. | clean | — | -0.6 | 14.3 |
| 43109 | Uganda Payments (Flutterwave — MTN MoMo) Uganda payments for AI agents — MTN MoMo via Flutterwave. Never holds funds. | clean | — | -0.6 | 14.3 |
| 43110 | United Kingdom Payments (Stripe — Stripe checkout) United Kingdom payments for AI agents — Stripe checkout via Stripe. Never holds funds. | clean | — | -0.6 | 14.3 |
| 43111 | Ukraine Payments (LiqPay — LiqPay cards / Apple Pay) Ukraine payments for AI agents — LiqPay cards / Apple Pay via LiqPay. Never holds funds. | clean | — | -0.6 | 14.3 |
| 43112 | Uruguay Payments (Mercado Pago — Mercado Pago wallet) Uruguay payments for AI agents — Mercado Pago wallet via Mercado Pago. Never holds funds. | clean | — | -0.6 | 14.3 |
| 43113 | United States Payments (Stripe — Stripe checkout) United States payments for AI agents — Stripe checkout via Stripe. Never holds funds. | clean | — | -0.6 | 14.3 |
| 43114 | Zambia Payments (Flutterwave — mobile money) Zambia payments for AI agents — mobile money via Flutterwave. Never holds funds. | clean | — | -0.6 | 14.3 |
| 43115 | Aigist Publish & manage shareable HTML/Markdown pages from your LLM, with access control. | clean | — | -0.6 | 14.3 |
| 43116 | DuckHub QR Menu Hosted MCP server to manage a restaurant menu from AI agents - 39 tools over the DuckHub API. | clean | — | -0.5 | 14.3 |
| 43117 | Lawstronaut Connect AI to millions of laws and court cases with the Lawstronaut MCP. | clean | — | -0.6 | 14.3 |
| 43118 | com.narrowhighway/concordance Deterministic claim verification with receipts across ~60 domains. No model in the loop. | clean | — | -0.6 | 14.3 |
| 43119 | com.policylayer/registry The MCP server that vets MCP servers: identity, risk grade and per-tool risk before you install. | clean | — | -0.6 | 14.3 |
| 43120 | TickerDB Pre-computed market data that improves agent reasoning, reduces token usage, and replaces pipelines. | clean | — | -0.6 | 14.3 |
| 43121 | Busymate DevTools Capture, inspect & debug HTTPS traffic across iOS, Android, browsers & backends — 304 MCP tools. | clean | — | -0.6 | 14.3 |
| 43122 | StitchAPI Docs Search and read the StitchAPI docs: search_docs finds relevant sections, get_doc reads a page. | clean | — | -0.5 | 14.3 |
| 43123 | io.github.3xpr1ment/repiscope Read-only MCP server: your agent sees all your sibling repos but structurally cannot touch them | clean | — | -0.6 | 14.3 |
| 43124 | Arc & Ledger Tax Tools Enrolled Agent tax tools: IRS notices, FBAR, LLC vs S-Corp, quarterly estimates & more. | clean | — | -0.6 | 14.3 |
| 43125 | io.github.BorisGujvin/dittu Turns a phone into a camera+Bluetooth remote so AI assistants can see and control any PC. | clean | — | -0.6 | 14.3 |
| 43126 | peek Exposes recorded browser sessions (rrweb DOM, console, network) to AI coding agents, fully local | medium | — | -0.6 | 14.3 |
| 43127 | io.github.Doucs91/hivelore Deterministic gate: blocks any commit whose diff reintroduces a documented team mistake. | clean | — | -0.6 | 14.3 |
| 43128 | io.github.FurlPay/furlpay-cli Stablecoin payments, swaps, stock orders, market data, travel booking, yield and card controls. | clean | — | -0.5 | 14.3 |
| 43129 | Word Is Bond Test the voice agents you run: scored transcripts, pass/fail verdicts, latency and WER metrics. | clean | — | -0.6 | 14.3 |
| 43130 | Wild Wallet — where agents get a body Agents browse Wild Wallet bodies + closets and file human-approved merge requests. | clean | — | -0.6 | 14.3 |
| 43131 | Stride20k x402 Data Gateway x402 analytics feed + 20+ pay-per-call agent tools over x402 (data, LLM, risk), no accounts. | clean | — | -0.6 | 14.3 |
| 43132 | io.github.NodeDex/nodedex Your project's decision history for agents: decisions, dead-ends, constraints - queryable, local. | clean | — | -0.6 | 14.3 |
| 43133 | io.github.PramodDutta/qaskills Search, inspect, and install 400+ QA testing skills from qaskills.sh into any MCP client. | clean | — | -0.6 | 14.3 |
| 43134 | io.github.Runewardd/runeward Governed execution cells for AI agents: Docker/K8s sandboxes with policy, audit, and approvals. | clean | — | -0.6 | 14.3 |
| 43135 | Librarian Deterministic ebook-to-markdown pipeline with MCP tools to browse, search, and read your books. | clean | — | -0.6 | 14.3 |
| 43136 | XFuel Submit AI inference to XFuel, pay per task (USDC via x402 or TFUEL), fetch/verify ZK proofs. | clean | — | -0.6 | 14.3 |
| 43137 | io.github.acarchidi/agentforge DeFi safety layer for AI agents: wallet safety, token risk, tx decode/simulate. 20 tools. | clean | — | -0.6 | 14.3 |
| 43138 | io.github.afghanfansmedia-ai/songcheck-mcp Is this song AI or human? Detect AI-generated music (Suno, Udio) from any AI agent. | clean | — | -0.6 | 14.3 |
| 43139 | Akeyless Agentic Runtime Authority Secretless database and cloud access via Akeyless RTA. Credentials never enter the model. | clean | — | -0.6 | 14.3 |
| 43140 | CAI MCP CAI MCP server — gives AI agents a custodial wallet, @cai.com email, and vault. | clean | — | -0.6 | 14.3 |
| 43141 | io.github.caraulani/euacc-mcp Live EU funding data in your AI: grant calls, programmes, consortium partners, VCs, incubators. | clean | — | -0.5 | 14.3 |
| 43142 | Heddle Content-addressed contracts and a verification cache that cut agent context by skipping proven code. | clean | — | -0.6 | 14.3 |
| 43143 | Purify Security Feeds Query CISA KEV / EPSS vulnerability feeds with full per-record provenance and auditable versions | clean | — | -0.6 | 14.3 |
| 43144 | NovaRail Discover, verify, and hire AI agents from the NovaRail marketplace, from your editor. | clean | — | -0.6 | 14.3 |
| 43145 | io.github.flagrix-io/flagrix Scan GitHub repos and profiles for malware before cloning — commit-pinned risk verdicts for agents | clean | — | -0.6 | 14.3 |
| 43146 | On-Demand-Books Find personalized puzzle books by first name from a 100,000+ title Shopify catalog. | clean | — | -0.6 | 14.3 |
| 43147 | io.github.iinniitt/defi-guard-mcp DeFi safety checks on Base before you sign: honeypot, owner-power scan, approval risk, Aave health. | clean | — | -0.5 | 14.3 |
| 43148 | io.github.kakunin-ai/kakunin X.509 identity, risk scoring, and audit logging for AI agents. MiCA + EU AI Act compliant. | clean | — | -0.6 | 14.3 |
| 43149 | io.github.kubently/kubently Troubleshoot Kubernetes agentically: natural-language cluster diagnosis via ask_kubently | clean | — | -0.6 | 14.3 |
| 43150 | Artifacts Self-hosted artifact publishing: POST HTML/JSX/Markdown/zip, get an unguessable URL on your domain | clean | — | -0.6 | 14.3 |
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.