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.
59,385
servers indexed
85
with verified activity
20.0
median score
21,857
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 |
|---|---|---|---|---|---|
| 51951 | io.github.Capataina/agentfulfyl Research storefront for AI agents: fixed GBP prices, evidence ledgers, citation-refund guarantee. | medium | — | -0.6 | 9.9 |
| 51952 | Compuute MCP Security Scanner Scan any public GitHub MCP-server repo for security issues. 37 MCP-specific L1 rules, 8 languages. | clean | — | -0.6 | 9.9 |
| 51953 | io.github.JienWeng/x402-osint Pay-per-call OSINT for AI agents: username + email recon in USDC on Base via x402. | medium | — | -0.6 | 9.9 |
| 51954 | io.github.Jing7ao/aihot-mcp AI HOT 资讯 MCP Server - 让 Claude Code 直接获取 AI 行业日报和动态 | clean | — | -0.5 | 9.9 |
| 51955 | io.github.Jing7ao/seedance-mcp Seedance AI 视频生成 MCP Server - 让 Claude Code 直接生成 AI 视频 | clean | — | -0.5 | 9.9 |
| 51956 | MCP Commerce Server Starter FastMCP commerce server starter: product catalog, search, and checkout. Deploy to Vercel in 5 min. | clean | — | -0.6 | 9.9 |
| 51957 | osu! MCP MCP server exposing the osu! API v2: player stats, scores, beatmap search, rankings. | clean | — | -0.6 | 9.9 |
| 51958 | io.github.SnipMCP/gadschain Google Ads MCP server. Read campaigns, manage budgets, pause/enable, add negative keywords. | clean | — | -0.6 | 9.9 |
| 51959 | Gridscoot AU price comparison via MCP — search, compare, track. 6 tools; anonymous demo (30/day/IP). | clean | — | -0.5 | 9.9 |
| 51960 | io.github.ad0750/regintel-mcp MCP server for the RegIntel API: regulatory data across 41 jurisdictions, 212 regulations. | clean | — | -0.6 | 9.9 |
| 51961 | Linear MCP (multi-workspace, PAT auth) Multi-workspace Linear MCP — PAT auth, 57 tools + 3 prompts, substrate enforcement, drop-in. | clean | — | -0.6 | 9.9 |
| 51962 | Simmer Trade prediction markets with AI agents — skill discovery, autoresearch, and execution. | clean | — | -0.6 | 9.9 |
| 51963 | io.github.aitor-alt/pixel-squads MCP Server for Pixel Squads — observe your AI agents as pixel-art characters in a live office | clean | — | -0.6 | 9.9 |
| 51964 | io.github.anp2protocol/anp2-mcp-server Economic protocol for AI agents — identity + reputation + credit + Sybil resistance (MCP bridge) | clean | — | -0.6 | 9.9 |
| 51965 | Bawbel Scanner Scan MCP servers and skill files for AVE vulnerabilities. Conformance scoring and threat intel. | clean | — | -0.6 | 9.9 |
| 51966 | Bawbel Scanner Security scanner for MCP servers and skill files. Detects AVE vulnerabilities before production. | clean | — | -0.6 | 9.9 |
| 51967 | Duvo MCP Governed retail, FMCG, and CPG operational tools: runs, cases, approvals, audit-ready execution. | clean | — | -0.6 | 9.9 |
| 51968 | io.github.evidai/agent-payment Stripe-style USDC billing for any API. 8 free demo services no signup. Non-custodial. | clean | — | -0.5 | 9.9 |
| 51969 | Scout Browser automation MCP server with 84 tools. Pure CDP, DOM diffing, vision hybrid. | clean | — | -0.6 | 9.9 |
| 51970 | A2ABench Public benchmark where agents submit Q&A answers and get scored on a leaderboard. | clean | — | -0.6 | 9.9 |
| 51971 | io.github.narekmalk/safedb-mcp A secure MCP server that lets AI agents query databases safely. | clean | — | -0.6 | 9.9 |
| 51972 | Phonon Monitoring + status pages set up by talking to Claude. Auto-detects 30+ SDKs and your URLs. | clean | — | -0.6 | 9.9 |
| 51973 | Rustok Wallet Self-custody Ethereum Agent Wallet. All chains enabled by default. User assumes all risks. | clean | — | -0.6 | 9.9 |
| 51974 | io.github.thegrenadinekid25/troth AI-powered spec-to-task decomposition and execution orchestration for coding agents. | clean | — | -0.6 | 9.9 |
| 51975 | Aegis Charter-bound defensive security copilot: secrets, obfuscation, deps, Dockerfile, IaC scans. | clean | — | -0.6 | 9.9 |
| 51976 | Agent Release Auditor Deterministic release gate for AI-written code and coding agents. | clean | — | -0.5 | 9.9 |
| 51977 | Cookie Consent Compliance Scanner Cookie consent scanner: GDPR, CCPA, GCMv2. PASS/FAIL compliance checklists with fix recommendations. | clean | — | -0.6 | 9.9 |
| 51978 | no.sladd/mcp Detect and redact Norwegian PII (fodselsnummer, names, health data) in text and PDFs. | medium | — | -0.6 | 9.9 |
| 51979 | Siima eSIM Search travel eSIM plans for 150+ countries and buy via Stripe link; eSIM QR delivered by email. | medium | — | -0.5 | 9.9 |
| 51980 | NotCVE — CVE & Vulnerability Intelligence CVE & vulnerability search: 365k+ CVEs/NotCVEs, CVSS, EPSS, CISA KEV, exploits, patches, versions. | medium | — | -0.6 | 9.9 |
| 51981 | AgentForge Turn rough requests into rigorously structured prompts, for any coding agent. | clean | — | -0.6 | 9.9 |
| 51982 | org.vicp-registry/vicp-registry Search 13,000+ US vaccine court (VICP) decisions: cases, court text, statistics, attorneys. Free. | medium | — | -0.6 | 9.9 |
| 51983 | Drawbridge Identity, secrets, and passwordless SSH provisioning for AI agents — Keycloak, vault, MCP tools. | clean | — | -0.6 | 9.9 |
| 51984 | Noon Barbari Backtesting Crypto backtesting tools: real backtests with robustness verdicts, daily signals and market data. | medium | — | -0.6 | 9.9 |
| 51985 | hood. — .hood name service Resolve .hood names on Robinhood Chain — forward/reverse, text records, availability & pricing. | medium | — | -0.6 | 9.8 |
| 51986 | Eevy Shopify CRO platform via MCP: 100+ tools for analytics, experiments, authoring, proven lift. | medium | — | -0.6 | 9.8 |
| 51987 | ai.promptsharp/promptsharp Professional prompt library over remote MCP: 13 verticals, free discovery scope. | medium | — | -0.6 | 9.8 |
| 51988 | Relaystation Pay-per-call agent infrastructure: file storage & handoff, compute tools, messaging, e-sign, KYC. | medium | — | -0.6 | 9.8 |
| 51989 | Statey An agent-native database over MCP: shared, validated, structured records in every AI chat. | medium | — | -0.6 | 9.8 |
| 51990 | app.ofia/latex Persistent AI LaTeX workspace: edit and compile multi-file projects, export publication-ready PDFs. | medium | — | -0.6 | 9.8 |
| 51991 | Steep Query metrics, targets, entities, and team data in your Steep workspace via MCP. | clean | — | -0.6 | 9.8 |
| 51992 | Artificial Wit AI MCP server unifying ERPs, CRMs, APIs and knowledge base for Claude, ChatGPT and Gemini. | medium | — | -0.6 | 9.8 |
| 51993 | com.domainposture/mcp Remote MCP server: 19 domain-hygiene and email-auth tools (DNS, SPF, DMARC, DKIM, TLS). | medium | — | -0.6 | 9.8 |
| 51994 | com.eurorackref/eurorack Citation-anchored Eurorack module reference: specs, compatibility, and patch techniques. | clean | — | -0.6 | 9.8 |
| 51995 | com.forgeorbital/agent-gate Local mandate gate and proof trail for AI agents that take consequential actions. | medium | — | -0.6 | 9.8 |
| 51996 | Kahve Tabela — Türkiye heritage, food & coast Read-only MCP tools for Turkey's heritage places, regional-food atlas, and Mavi Koy coastal atlas. | medium | — | -0.6 | 9.8 |
| 51997 | com.outliyr/agent-tools Run the Energy Leak Quiz, match biohacking gear, and build a longevity stack. Free, no API key. | medium | — | -0.6 | 9.8 |
| 51998 | Papaya Pay Any Bill (US) Pay any US bill in a snap, right from your chat — utilities, medical, rent, parking tickets & more. | medium | — | -0.6 | 9.8 |
| 51999 | Pingfyr Schedule reminders for AI agents via email, webhook, Slack, Discord, Telegram, or Google Calendar. | clean | — | -0.6 | 9.8 |
| 52000 | pixserp Live AI-native web search with citations. One tool for every MCP client. Flat per-request pricing. | clean | — | -0.6 | 9.8 |
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.