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.
41,986
servers indexed
88
with verified activity
21.0
median score
13,104
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 |
|---|---|---|---|---|---|
| 6551 | io.github.adlane-app/mcp-server Read-only MCP connector for Adlane workspaces, Google and Meta ad accounts and campaign reports. | clean | — | — | 24.0 |
| 6552 | Leporis WhatsApp Send and read WhatsApp messages on your Leporis account from AI coding agents, via your own API key. | clean | — | — | 24.0 |
| 6553 | io.github.admin978/canvas-mcp Local-first MCP server for Canvas LMS. Stdio transport, no third-party broker. | clean | — | — | 24.0 |
| 6554 | Provena Agent Memory Self-hosted MCP memory for AI agents: persistent context with evidence-backed claims. | clean | — | — | 24.0 |
| 6555 | Email Finder Server Extract emails and phones from any website via Apify. | clean | — | — | 24.0 |
| 6556 | FB Ad Intel Server Meta ad intelligence via Apify: ad copy, CTAs, platforms, advertisers. | clean | — | — | 24.0 |
| 6557 | Maps Leads Server Google Maps business leads via Apify: name, phone, website, rating. | clean | — | — | 24.0 |
| 6558 | Meta Ad Intel Server Meta ads plus advertiser contacts via Apify enrichment. | clean | — | — | 24.0 |
| 6559 | Yelp Leads Server Yelp business leads via Apify: rating, phone, price range. | clean | — | — | 24.0 |
| 6560 | abcop ABC complexity gate for AI-written code with an MCP inspection tool. | clean | — | — | 24.0 |
| 6561 | rrubocop Fast RuboCop-compatible Ruby linter with MCP inspect and autocorrect tools. | clean | — | — | 24.0 |
| 6562 | AegisGate MCP Secure MCP server framework with 23 security layers and ML threat detection. Zero deps. | clean | — | — | 24.0 |
| 6563 | Mingle — Agent-Native Connection Protocol Meet the people you're looking for. Your agent composes, you approve. Nothing scores or ranks you. | medium | — | — | 24.0 |
| 6564 | io.github.aernouddekker/mailappmcp MCP server for macOS Mail.app — gives Claude native email access via AppleScript | clean | — | — | 24.0 |
| 6565 | io.github.aeronlabs/aeron-wallet Non-custodial agent wallet for Robinhood Chain. Pays x402 requests in USDG. | clean | — | — | 24.0 |
| 6566 | ACI Risk Indicators Counterparty risk indicators for digital asset yield providers across 9 modules. 7 tools. | clean | — | -62.0 | 24.0 |
| 6567 | Computer Use Turbo Let any AI agent operate desktop apps on macOS, Windows and Linux, in the background and safely. | clean | — | — | 24.0 |
| 6568 | Instagram Profile MCP Server Instagram profiles for AI agents — followers, similar accounts, keyword and location search. | clean | — | — | 24.0 |
| 6569 | Zillow MCP Server Zillow homes and agent contacts for AI agents — search by ZIP, by URL, or look up a zpid. | clean | — | — | 24.0 |
| 6570 | affset Run affset from chat: stats, campaigns, zones, payouts, targeting, and team. | clean | — | — | 24.0 |
| 6571 | Baserow Schema MCP Generic Baserow API client MCP server with automatic 2FA (TOTP) auth and OpenAPI validation. | clean | — | — | 24.0 |
| 6572 | MVR API - Minimum Viable Relationships Read-only MVR preflight for trust, permission, evidence gaps, and African market-entry readiness. | clean | — | — | 24.0 |
| 6573 | Dayanak Citation-safe Turkish legal research: court decisions and legislation from official sources. | clean | — | — | 24.0 |
| 6574 | Doktor Turkish health law for physicians: official legislation and high court decisions, source-grounded. | clean | — | — | 24.0 |
| 6575 | io.github.afurlane/copilot-datagate Policy-driven, read-only MCP server for safe database access from AI tools. | clean | — | — | 24.0 |
| 6576 | io.github.agencyenterprise/aiseo-audit Audit web pages for AI search readiness with evidence-tiered factors and pipeline-stage scores. | clean | — | — | 24.0 |
| 6577 | agend-sh Persistent Linux environments for AI agents, with interactive terminals and HTTPS previews. | clean | — | — | 24.0 |
| 6578 | Agent Index P2P Agent Index MCP — publish and search decentralized web indexes over libp2p. | clean | — | — | 24.0 |
| 6579 | Polymarket Paper Trader Polymarket paper trading for AI agents: $10k paper money, real order books, official fees. | clean | — | — | 24.0 |
| 6580 | Agent Passport System — Cryptographic Identity for AI Agents Cryptographic identity, delegation, governance, and commerce for AI agents. 152 tools. | medium | — | — | 24.0 |
| 6581 | io.github.agent-resolve/agent-resolve-mcp Escrow, verification, and settlement platform for AI agents hiring other AI agents. | clean | — | — | 24.0 |
| 6582 | Agentcity Robinhood Chain Research Read-only Robinhood Chain token research via GMGN, built for Agentcity agents and any MCP client. | clean | — | — | 24.0 |
| 6583 | io.github.agente-dev/wfirma-mcp Unofficial read-only MCP server for the wFirma API v2: invoices, contractors, expenses, payments. | clean | — | — | 24.0 |
| 6584 | Agentic HIL Develop firmware on the real board behind a debug probe: flash, reset, UART and CAN, policy-gated. | clean | — | — | 24.0 |
| 6585 | Secret Scan Check text for leaked credentials before an agent writes or commits it. Runs locally. | clean | — | — | 24.0 |
| 6586 | Axint Proof and repair for Apple coding agents: validate Swift, run Xcode evidence, and repair failures. | clean | — | — | 24.0 |
| 6587 | Agentic Reputation Gateway Read-only gateway for durable agent identity, consent, recognized work, and signed receipts. | clean | — | — | 24.0 |
| 6588 | Kairos Relationship Memory Free MCP: relationship_memory validate, store (local), retrieve — portable interlocutor cards v1. | clean | — | — | 24.0 |
| 6589 | io.github.agentready-market/audit AgentReady.market audit: can an AI shopping agent find, understand and BUY on this store? /100. | clean | — | — | 24.0 |
| 6590 | AgentSearch (agentsearchhq.com) Web search, extract and JS render at $0.005/call (x402, USDC on Base), plus a free Review Board. | clean | — | — | 24.0 |
| 6591 | yieldhunter Risk-adjusted stablecoin yield ranks for other agents. Research only. Never holds keys or executes. | clean | — | — | 24.0 |
| 6592 | yieldsentinel Policy check on a described yield position. Complement to yieldhunter. Research only. | clean | — | — | 24.0 |
| 6593 | AgentStack (agentstack.tech) Backend for AI agents: one batched tool over ~668 actions (hosting, storage, auth, payments). | clean | — | — | 24.0 |
| 6594 | AgentToolbox Docs Pack Query-matched doc excerpts in one JSON response. $0.01 USDC on Base via x402, pay-per-success. | clean | — | — | 24.0 |
| 6595 | AgentTrust — Pre-Invocation AI Agent Trust & Reliability Checks Check an AI agent endpoint before you call it: read-only, no API key, returns a trustDecision. | clean | — | — | 24.0 |
| 6596 | io.github.agentwares/agent-access-index Whether an AI agent may fetch a URL, on what terms, and at what price. Free, no key, no signup. | clean | — | — | 24.0 |
| 6597 | agentcheck Synthetic checks, nightly regression replay and model-drift alerts for AI agents | clean | — | — | 24.0 |
| 6598 | agentguard MCP policy proxy: spend caps, approvals for destructive tools, kill switch, dry-run, audit log. | clean | — | — | 24.0 |
| 6599 | agentguard — policy proxy for agent tool calls Free spend report from an agent log, no key. Hosted proxies: caps, audit export, buy calls. | clean | — | — | 24.0 |
| 6600 | Real estate deal memo Real estate deal memo from a US address: AVM, rent, comps, cap rate, cash-on-cash, DSCR, red flags. | 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.