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 |
|---|---|---|---|---|---|
| 3551 | mac-control-mcp Native Swift macOS automation — 153 tools: AX, EventKit, voice, browser DOM, undo. | medium | — | — | 24.0 |
| 3552 | io.github.AdelElo13/neuromcp Semantic memory for AI agents with hybrid search, knowledge graph, and consolidation | medium | — | — | 24.0 |
| 3553 | Blog2Social - Social Media Publishing Connect AI agents to Blog2Social and automate social media content workflows via MCP. | clean | — | — | 24.0 |
| 3554 | io.github.Adeniyikayodee/gagelink River level, streamflow, floods and basins from USGS, NOAA, Hub'Eau, UK Environment Agency, SWOT | clean | — | — | 24.0 |
| 3555 | Nigeria Postcode Validate, look up and resolve addresses to Nigeria's NIPOST digital postcodes (NDAPS). | clean | — | — | 24.0 |
| 3556 | Bangermap Find YouTube outliers, videos that beat their channel's own baseline, on your own free API key. | clean | — | — | 24.0 |
| 3557 | Specularis AI Visibility Audit Free AI visibility (GEO/AEO) audit: can ChatGPT, Claude and Perplexity find and cite your website? | clean | — | — | 24.0 |
| 3558 | docmcp — Word & Excel files Real .docx and .xlsx files from structured data, with automatic Hebrew/Arabic RTL. | clean | — | — | 24.0 |
| 3559 | io.github.AdithyaVardan1/panini-connector-mcp Install + verify the panini-connector SDK on self-hosted sites, driven by AI agents. | clean | — | — | 24.0 |
| 3560 | io.github.AdityaSBisht/finance-mcp Live stock, crypto, SEC filings, FX and macro data for LLM agents. No API keys. | clean | — | — | 24.0 |
| 3561 | io.github.Aelindra/mobile-agent-harness Android device automation for AI agents: MCP server, CLI, and plugin runtime over adb. | clean | — | — | 24.0 |
| 3562 | io.github.AetherAI3/agent-browser Self-hosted Chrome for AI agents, with a live noVNC view a human can take over. | clean | — | — | 24.0 |
| 3563 | io.github.Aethis-ai/aethis-mcp Deterministic eligibility decisions and test-driven rule authoring via the Aethis developer API. | clean | — | — | 24.0 |
| 3564 | Africa Data Bank Trusted African data, provenance, citations, and catalog search for AI agents. | clean | — | — | 24.0 |
| 3565 | Easy2257 Read your 18 U.S.C. 2257 compliance records: what is outstanding, expiring, or certified. | clean | — | — | 24.0 |
| 3566 | Hiberden Read and verify your local media archive's 3-2-1 coverage across tape, disk, NAS, and cloud. | clean | — | — | 24.0 |
| 3567 | Agent360 Browser MCP Drive your real, logged-in Chrome from any AI agent - 40 tools. Needs our Chrome extension too. | clean | — | — | 24.0 |
| 3568 | io.github.Agent360dk/computer-mcp macOS computer use with the guardrails on: passwords blacked out, writes need consent, all logged. | medium | — | — | 24.0 |
| 3569 | ScreenshotMCP Desktop and mobile website screenshots plus page context for AI agents and automation workflows. | clean | — | — | 24.0 |
| 3570 | Agent Margin Router 38 x402 pay-per-call tools for AI agents (USDC/USDT on Base): web, crypto, on-chain, geo, packages | clean | — | — | 24.0 |
| 3571 | Agent Search Pro Live web search and research synthesis for agents, with free samples and x402 USDC payments. | clean | — | — | 24.0 |
| 3572 | io.github.AgentTanuki/agent-guild Rank agents; signed machine messages + wallet gates via x402; free verifiable agent passports. | clean | — | — | 24.0 |
| 3573 | io.github.AgentTanuki/x402-payment-safety Authorize x402 payments before signing with request-bound, signed safety decisions. | clean | — | — | 24.0 |
| 3574 | AgentTax US sales/use tax, nexus thresholds, capital gains and 1099-DA tools for AI agent transactions. | clean | — | — | 24.0 |
| 3575 | ModelShortlist Local BYOK MCP for AI model shortlisting using OpenRouter + Artificial Analysis. | clean | — | — | 24.0 |
| 3576 | io.github.Agentled/mcp-server Intelligent AI workflow orchestration with long-term memory, 100+ integrations, and unified credits. | clean | — | — | 24.0 |
| 3577 | Agents Get Paid Kit — x402 MCP + Unlock ($49) x402 MCP get-paid path: USDC, spend caps, AUP, $49 kit. CAPTCHA/web-unlock for payment-ready agents. | clean | — | — | 24.0 |
| 3578 | AgentsKit Registry Discover open-source AI agents and get source-owned installation instructions through MCP. | clean | — | — | 24.0 |
| 3579 | Doc Bridge Resolve documentation ownership, edit roots, checks, and human handoffs before an agent edits code. | clean | — | — | 24.0 |
| 3580 | Dibs Tells an AI agent when another is already doing its work. Board, typed mail, directory claims. | clean | — | — | 24.0 |
| 3581 | Agenzax B2B network where companies' AI agents discover, negotiate, and build reputation. E2E-encrypted. | clean | — | — | 24.0 |
| 3582 | IsolatedTester — TinkyVision system Isolated macOS app tests, MCP images, OCR/ASCII frames, accessibility and evidence reports. | clean | — | — | 24.0 |
| 3583 | TinkyVision Screen observation, OCR and permission-controlled app input over MCP for Apple silicon Macs. | clean | — | — | 24.0 |
| 3584 | io.github.Aggrete/aggrete MCP policy proxy: enforces a code of conduct across connectors before the upstream is called. | clean | — | — | 24.0 |
| 3585 | io.github.Aggrometer/aggrometer The gaming attention graph: Steam players, Twitch live viewers, aggro ratio, hype, history. | clean | — | — | 24.0 |
| 3586 | io.github.Ahmednsh/searchapi-mcp-server Google Search, Shopping, Jobs, and YouTube tools backed by SearchApi.io | clean | — | — | 24.0 |
| 3587 | DropEngine x402 Agent Services AI Agent Utility Layer for agent safety, web monitoring, crypto research and tool discovery. | clean | — | — | 24.0 |
| 3588 | ReactFrame Search ReactFrame's React + Tailwind + Motion components, install free ones and price premium picks. | clean | — | — | 24.0 |
| 3589 | io.github.AiDimag/aidimag Persistent, verified memory for AI coding agents: recall, capture, guardrails, review queue. | clean | — | — | 24.0 |
| 3590 | Aident Loadout Connect any AI agent to 1,000+ apps and 27,000+ actions through one remote MCP server (OAuth). | clean | — | — | 24.0 |
| 3591 | io.github.Aidress-ai/aidress Verify, discover, and rate AI agents before transacting. | clean | — | — | 24.0 |
| 3592 | Mailcannon AI-powered email outreach platform — send campaigns with deliverability tracking. | clean | — | — | 24.0 |
| 3593 | Data Prism Fail-closed privacy layer that pseudonymises enterprise API data for LLM agents and MCP clients. | clean | — | — | 24.0 |
| 3594 | DaVinci Resolve Local Bridge MCP Control DaVinci Resolve from any AI assistant. 215 MCP tools covering the full Resolve API. | clean | — | — | 24.0 |
| 3595 | AirTreks MCP Multi-city flight routing intelligence — plan RTW trips, validate alliances, get carrier picks. | clean | — | — | 24.0 |
| 3596 | Vibe Test — Browser Testing Agent Code-aware browser testing agent — 14 Playwright tools for AI code editors via MCP | clean | — | — | 24.0 |
| 3597 | io.github.Aitejiu/jev Jev judgments for agents: injection scanning, shell risk gating, ranking | clean | — | — | 24.0 |
| 3598 | AitherOS ADK Agent runtime with typed memory, knowledge and code graphs, plus file and web tools | clean | — | — | 24.0 |
| 3599 | Aito Predictions over your own data with $p and $why, no model training; says when Aito does not fit. | clean | — | — | 24.0 |
| 3600 | Vouch Vouch — independently measured reliability scores for MCP tools, not self-reported claims. | 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.