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 |
|---|---|---|---|---|---|
| 48151 | io.github.meloliva14/verity-mcp Fail-closed verify-before-you-act gate for AI agents. Signed receipts. Pay-per-call via x402. | clean | — | -0.5 | 13.5 |
| 48152 | Apex (smartapex.uk) AI Component Card Store Run verified read-only code tools: quant diagnostics + agent-ops preflight, no source exposure. | clean | — | -0.6 | 13.5 |
| 48153 | io.github.nickjlamb/opengate-mcp Check whether an AI answer is grounded in its context — deterministic, no LLM judge. | clean | — | -0.6 | 13.5 |
| 48154 | Nogra Verify-before-done trust layer for AI-assisted work. 32 tools, local-first, no credentials. | clean | — | -0.6 | 13.5 |
| 48155 | Ratary Memory MCP Persistent coding memory for AI assistants. MCP stdio, hybrid search, graph, context. | clean | — | -0.6 | 13.5 |
| 48156 | io.github.ozers/hooksense Webhook & callback layer for AI agents: create a URL, wait_for_callback, and verify over MCP. | clean | — | -0.6 | 13.5 |
| 48157 | io.github.pfeilisolana/scry-mcp Keyless MCP bridge to Scry Solana wallet intel: free coverage check, catalog, x402 paid endpoints. | clean | — | -0.6 | 13.5 |
| 48158 | io.github.pranavbhosale25/eia-mcp-gridsense MCP server for US electricity grid data: fuel mix, demand, retail prices, CO2 emissions | clean | — | -0.6 | 13.5 |
| 48159 | Quality Screener Screen and score stocks with the Quality Screener engine: filters, custom scores, and history. | clean | — | -0.6 | 13.5 |
| 48160 | io.github.rabdulsal/appstore-release-mcp App Store release pilot — version bump, TestFlight upload, metadata, review submission | clean | — | -0.6 | 13.5 |
| 48161 | io.github.recordant/recordant Patent-pending diagnostic + decisions-ledger engine with operator briefs and an MCP console. | clean | — | -0.5 | 13.5 |
| 48162 | io.github.replenhq/replen A local intelligence layer for AI coding agents. Maps your repos, matches the open-source frontier. | clean | — | -0.6 | 13.5 |
| 48163 | Apex by LeadShark — discovery No-auth discovery endpoint for Apex by LeadShark — governed LinkedIn hands for AI agents. | clean | — | -0.5 | 13.5 |
| 48164 | io.github.sattyamjjain/whycant Roast any AI agent idea from your IDE: verdict tier, readiness score, top risk, shareable URL. | clean | — | -0.5 | 13.5 |
| 48165 | io.github.seanmarkwei/agentram-mcp Model Context Protocol server for AgentRAM. Persistent memory for AI agents. | clean | — | -0.6 | 13.5 |
| 48166 | io.github.segentic-lab/codelens-mcp Deterministic code maps for AI agents: 7 tree-sitter tools for TS/JS/Py — map, find, function_body | clean | — | -0.6 | 13.5 |
| 48167 | io.github.segentic-lab/lens-mcp Deterministic navigation maps over code + markdown + Prisma for AI agents: 13 MCP tools | clean | — | -0.6 | 13.5 |
| 48168 | io.github.shubhtoy/github-project-info Read public GitHub Projects v2 boards without auth — items, fields, story points, priority. | clean | — | -0.6 | 13.5 |
| 48169 | io.github.smartpolicy-protocol/smartpolicy Runtime authorization for AI agents and smart contracts via an immutable on-chain policy registry | clean | — | -0.6 | 13.5 |
| 48170 | StandardGraph 158,000+ K-12 education standards across 300 curriculum systems, cross-referenced via NLP. | clean | — | -0.6 | 13.5 |
| 48171 | io.github.tarunlnmiit/autopilot-jobhunt Agentic job hunt: scan careers pages, score against your resume, draft applications. Never applies. | clean | — | -0.5 | 13.5 |
| 48172 | io.github.tarunlnmiit/inbox-to-action Agentic Gmail triage: classify, summarize, extract tasks, draft replies. Never sends. | clean | — | -0.5 | 13.5 |
| 48173 | io.github.terminalis/appcraft Deterministic Android app compiler — agents write a YAML model, the compiler emits the native app. | clean | — | -0.6 | 13.5 |
| 48174 | io.github.vk0dev/agent-claim-mcp File-claim coordination for parallel AI coding agents: claim files before edits, no stomping. | clean | — | -0.6 | 13.5 |
| 48175 | io.github.vk0dev/agent-cost-mcp Cost Guard for Claude Code: per-tool ROI, subagent attribution, anomaly/forecast/budget guards. | clean | — | -0.6 | 13.5 |
| 48176 | io.github.zachlikefolio/tunnel-mcp Direct end-to-end-encrypted tunnel between Claude agents — two-party or a room of up to 16. | medium | — | -0.6 | 13.5 |
| 48177 | io.github.zexiro/waitloop Agent-first waitlists: hosted signup pages with referral ranking. One tool call returns a live page. | clean | — | -0.5 | 13.5 |
| 48178 | io.settlemesh/cli Deploy and monetize agent-built apps: login, database, usage billing, and end-user-pays. | medium | — | -0.6 | 13.5 |
| 48179 | services.gera/mcp-gera-indices Discover, resolve & cite Gera named UK NHS/OGL public-data indices with real source provenance. | clean | — | -0.6 | 13.5 |
| 48180 | Biel.ai Query your product docs from AI tools. Source-cited answers from your indexed documentation. | clean | — | -0.6 | 13.4 |
| 48181 | ai.dataecho/mcp Deploy files, sites, and Dockerfile apps to live URLs + private drives for agent memory. | clean | — | -0.6 | 13.4 |
| 48182 | ai.gatetest.www/gatetest 120-module QA gate. Give Claude eyes (screenshots), ears (Sentry errors), and hands (verify fixes). | clean | — | -0.6 | 13.4 |
| 48183 | Gachi Data API — Japan Station & Accessibility Data Deep, obscure Japanese station, accessibility & hazard data for AI agents. English-first. | clean | — | -0.6 | 13.4 |
| 48184 | Most Recommended Books Read-only MCP server for verified book recommendations and reading lists. | clean | — | -0.6 | 13.4 |
| 48185 | dev.mailkite/agent-mail Give an AI agent its own inbox — receive email as a webhook, send over a verified domain. | clean | — | -0.5 | 13.4 |
| 48186 | dev.mailkite/email-agent Email for AI agents — send, receive as a webhook, manage domains, templates, routing. | clean | — | -0.5 | 13.4 |
| 48187 | dev.mailkite/inbound-email Turn inbound email into a webhook — verify, parse, route, and store incoming messages. | clean | — | -0.5 | 13.4 |
| 48188 | dev.mailkite/mail-receive Receive inbound email as clean JSON — manage domains, routes, and webhooks. MailKite. | clean | — | -0.5 | 13.4 |
| 48189 | dev.mailkite/mail-send Send transactional email over a verified domain — templates, attachments, custom headers. | clean | — | -0.5 | 13.4 |
| 48190 | dev.mailkite/mailkite Send email, manage domains, DNS, webhooks, templates, and inbound routing on MailKite | clean | — | -0.6 | 13.4 |
| 48191 | AsterPay — EUR Settlement for AI Agents EUR settlement + trust for AI agent commerce: budgets, KYA, merchant discovery. 22 tools. | clean | — | -0.5 | 13.4 |
| 48192 | Faultline Check infrastructure health, manage incidents, and run runbooks in Faultline. | clean | — | -0.6 | 13.4 |
| 48193 | HTTP HTTP/REST client with saved collections, env secrets, and SSRF-safe host allowlisting. | clean | — | -0.6 | 13.4 |
| 48194 | SQL Read-only SQL querying + schema introspection over Postgres & SQLite, with a gated write mode. | clean | — | -0.6 | 13.4 |
| 48195 | io.github.Al-Adnane/kasbah-mcp Governance layer for agentic AI — signed, verifiable receipts for every agent action. | clean | — | -0.6 | 13.4 |
| 48196 | io.github.Alightttt/chesswithclaw Play chess live against your own personal AI agent — OpenClaw, Hermes, and similar. | clean | — | -0.5 | 13.4 |
| 48197 | io.github.BE-DCE/bedc-mcp MCP server for Dual Canvas Execution (DCE) - use with Polsia, Cursor, Claude, and other MCP clients | clean | — | -0.6 | 13.4 |
| 48198 | io.github.CakeRepository/1password MCP server for 1Password service accounts — tools and resources for vaults and credentials | clean | — | -0.5 | 13.4 |
| 48199 | io.github.DIDA-AI/hotelbooking Hotel Booking MCP Server | info | — | -7.6 | 13.4 |
| 48200 | io.github.H129hj/checkmcp Audit any MCP server's security & quality — OWASP MCP Top 10 + explainable 0-100 MCP Score | clean | — | -0.6 | 13.4 |
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.