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 |
|---|---|---|---|---|---|
| 4651 | MAL MCP Server MyAnimeList MCP server: Tenrai-powered reads plus official MAL personal-list management. | clean | — | — | 24.0 |
| 4652 | Steam MCP Server Steam store/game data (no key) plus player profiles, libraries and achievements (Steam Web API). | clean | — | — | 24.0 |
| 4653 | TMDB MCP Server MCP server for The Movie Database (TMDB) with IMDb/Rotten Tomatoes/Metacritic ratings via OMDb. | clean | — | — | 24.0 |
| 4654 | io.github.Grubbomatic/crawl-readiness Audit any site for 50+ AI crawlers, generate llms.txt, robots.txt and schema, track AI mentions. | clean | — | — | 24.0 |
| 4655 | io.github.GuangminJu/mellos-mapping Live layered dependency map for bottom-up development, drawn by the agent in a terminal pane. | clean | — | — | 24.0 |
| 4656 | io.github.Guard-Core/guard-core-mcp Guard Core security MCP: SecurityConfig validation, docs search, live threat detection. | clean | — | — | 24.0 |
| 4657 | io.github.GuardBee/audit-gap-auditor OWASP MCP08 audit/telemetry gaps: missing tool-call logs, raw args in logs, disabled audit | clean | — | — | 24.0 |
| 4658 | io.github.GuardBee/context-oversharing-auditor OWASP MCP10 context oversharing: session dumps, unscoped memory, shared context, prompt leaks | clean | — | — | 24.0 |
| 4659 | io.github.GuardBee/mcp-server-auditor Scans MCP server tool definitions for excessive agency, injection sinks, hardcoded secrets | clean | — | — | 24.0 |
| 4660 | io.github.GuardBee/oauth-auditor Scans MCP server auth code for OAuth 2.1 anti-patterns: token passthrough, missing audience | clean | — | — | 24.0 |
| 4661 | io.github.GuardBee/owasp-scan Unified OWASP MCP Top 10 scan — path or live tools/list, A–F grade, SARIF | clean | — | — | 24.0 |
| 4662 | io.github.GuardBee/prompt-injection-scanner Scans RAG content/scraped pages for indirect prompt injection | clean | — | — | 24.0 |
| 4663 | io.github.GuardBee/prompt-leak-scanner Catches leaked credentials and PII in outbound LLM prompts | clean | — | — | 24.0 |
| 4664 | io.github.GuardBee/secret-scanner Scans files for leaked secrets and API keys | clean | — | — | 24.0 |
| 4665 | io.github.GuardBee/security-proxy MCP gateway: many servers, one policy, lethal-trifecta blocking, PII masking, audit log | clean | — | — | 24.0 |
| 4666 | io.github.GuardBee/security-suite Bundle of secret-scanner, dependency-auditor, ssl-inspector, and dns-intelligence | clean | — | — | 24.0 |
| 4667 | io.github.GuardBee/tool-poisoning-scanner Scans MCP tool definitions for hidden instructions and confused-deputy sinks | clean | — | — | 24.0 |
| 4668 | io.github.GuardBee/toxic-flow-auditor Finds lethal-trifecta toxic flows in MCP tool catalogs: untrusted input, sensitive data, egress | clean | — | — | 24.0 |
| 4669 | Guava Wallet Intelligence Crypto security, honeypot detection, wallet analysis, and token risk scoring across 31 blockchains. | clean | — | — | 24.0 |
| 4670 | QECTOR Quantum Error Correction Local quantum error correction tools; decoder output verified against H c = s (mod 2). | clean | — | — | 24.0 |
| 4671 | GetABrain Real human judgment as agent tools — ask a question, get a structured human answer back. | clean | — | — | 24.0 |
| 4672 | WhitePact AI governance MCP server: trust scoring, guardrails, bias/hallucination detection, compliance. | clean | — | — | 24.0 |
| 4673 | io.github.HMAKT99/akf Trust metadata for AI agents — check files before building on them, stamp verified work. | clean | — | — | 24.0 |
| 4674 | JMRI MCP JMRI voice/chat control for DCC model railroads | clean | — | — | 24.0 |
| 4675 | HQBase Connect AI agents to your self-hosted HQBase shared email workspace. | clean | — | — | 24.0 |
| 4676 | io.github.HUANGCHIHHUNGLeo/claude-real-video Let any LLM watch a video locally — and search everything it has ever watched. | clean | — | — | 24.0 |
| 4677 | HYPD AI - Paid Ads & Analytics Google Ads, Meta (Facebook) Ads, GA4 and Merchant Center analysis in plain language. Read-only. | clean | — | — | 24.0 |
| 4678 | MAX+plus II MCP / 数字电路 AI 工具 MAX+plus II / MaxPlus2 MCP: GDF/SYM/SCF, compile/simulation. 原理图、波形、编译仿真与 Windows 自动化。 | clean | — | — | 24.0 |
| 4679 | io.github.HalidSaglam/saglitzdesign-mcp Expert design & marketing MCP: UI/UX, design languages, SEO/GEO, tokens, a11y, recipes. | clean | — | — | 24.0 |
| 4680 | Agent Failure Archive 186 real AI agent post-mortems, 107 of them measurement failures. Free tools, paid via x402. | clean | — | — | 24.0 |
| 4681 | ProjGraph MCP Server Analyze .NET solutions: Generate Mermaid graphs, ERDs, class diagrams, and project metrics. | clean | — | — | 24.0 |
| 4682 | Lockkeeper Routes each task to the few skills, MCP servers and tools that fit it. | clean | — | — | 24.0 |
| 4683 | io.github.HappyMealSteak/apizone Real-time status & uptime monitoring for 294 popular APIs — is it down, and how reliable? | clean | — | — | 24.0 |
| 4684 | AgentExec WebMCP & Base L2 Gateway Monetization and execution gateway for autonomous AI agents on Base Mainnet | clean | — | — | 24.0 |
| 4685 | io.github.HarimxChoi/google-surf-mcp Web, academic and code search with graph RAG, data lineage, ontology and cross-project schema links. | clean | — | — | 24.0 |
| 4686 | io.github.HarleyCoops/workspace-alberta Canadian procurement intelligence: CanadaBuys and Alberta tenders, ranked for your shop. | clean | — | — | 24.0 |
| 4687 | Morse — Telegraph in Telegram Ask Telegraph's ranked miners from any MCP client, no wallet. Morse pays; each answer has a receipt. | clean | — | — | 24.0 |
| 4688 | io.github.Harusame64/desktop-touch-mcp Computer-use MCP for Windows 10/11: 32 tools — screenshot, UIA, Chrome CDP, type/click/scroll, VBA. | clean | — | — | 24.0 |
| 4689 | Mirofy Ask a repository what depends on what. Every answer cites the file, line and commit it came from. | clean | — | — | 24.0 |
| 4690 | io.github.Hashi-Kazu/ai-test-process-mcp AI-assisted MCP server for JSTQB-based test planning, design, review, and analysis. | clean | — | — | 24.0 |
| 4691 | Hashlock Markets Non-custodial cross-chain OTC for AI agents: sealed RFQ, negotiation, HTLC atomic swaps. Testnet. | clean | — | — | 24.0 |
| 4692 | Stock Image MCP Search and download stock images from Unsplash, Pexels, Pixabay, Freepik, StockVault, and Burst | clean | — | — | 24.0 |
| 4693 | io.github.Hasned-spec/ox402-utils 47 micro-priced utilities: search, screenshots, OCR, whois, prices, video downloads. x402 USDC. | clean | — | — | 24.0 |
| 4694 | Arkon Vault Private projects, preflight, decisions, and handoffs that keep work continuous across AI tools. | clean | — | — | 24.0 |
| 4695 | io.github.HelgDemidov/refigure Convert DOCX/XLSX to Markdown — native chart-data extraction, optional VLM for figures | clean | — | — | 24.0 |
| 4696 | agentpay Enforced budgets for agents paying x402 APIs: the gateway holds the wallet, not the agent. | clean | — | — | 24.0 |
| 4697 | Anti-Vibe Read coding-agent output one sentence at a time, skim it by heading, or speed-read it. | clean | — | — | 24.0 |
| 4698 | io.github.Helm-Protocol/openttt-pot Cryptographic audit trail for Claude Code workflows — tamper-proof timestamps, IETF TTTPS compliant. | clean | — | — | 24.0 |
| 4699 | AnythingMCP Any REST/SOAP/GraphQL/OData/SQL API as MCP tools for Claude & ChatGPT. 353 connectors: SAP, ERP. | clean | — | — | 24.0 |
| 4700 | Mansa African Financial Reference Data African bank & SWIFT codes, NUBAN resolution, mobile networks, holidays and ISO 4217 currencies. | 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.