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.
54,385
servers indexed
86
with verified activity
20.0
median score
19,556
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 |
|---|---|---|---|---|---|
| 43801 | app.hoaster/hoaster Hosts AI-generated web content (HTML, images, SVG, JSON) at a public URL, with custom domains. | clean | — | -0.6 | 13.3 |
| 43802 | LaunchTrust Compliance & security scan for your app: secrets, exposed files, headers, privacy, AI-disclosure. | clean | — | -0.5 | 13.3 |
| 43803 | Datalastic Vessel Tracking & Maritime Intelligence Vessel tracking for 750,000+ ships, with ownership, inspections, port records, routes, and more. | clean | — | -0.6 | 13.3 |
| 43804 | Pairoa Your AI meets theirs before you do — private matching for needs, offers, and opportunities over MCP. | clean | — | -0.6 | 13.3 |
| 43805 | com.pulsemcp/google-flights MCP server for searching Google Flights — flight search, date grid pricing, and airport lookup. | clean | — | -0.6 | 13.3 |
| 43806 | com.pulsemcp/remote-filesystem MCP server for remote filesystem operations on cloud storage (Google Cloud Storage). | clean | — | -0.6 | 13.3 |
| 43807 | Social Champ Connect AI agents to Social Champ: manage channels, posts, AI content, queue, and approvals. | clean | — | -0.6 | 13.3 |
| 43808 | com.startupnamegenerator/name-tools Generate startup names with an available .com, checked live, then screen US and EU trademarks. | clean | — | -0.6 | 13.3 |
| 43809 | Verifly Email verification for AI agents — verify, clean & validate emails; self-onboard + crypto pay | clean | — | -0.6 | 13.3 |
| 43810 | info.agentrank/agentrank Is this AI agent or x402 service real and settlement-backed before you pay it? Trust check. | clean | — | -0.6 | 13.3 |
| 43811 | io.github.AliAkhtari78/spotifyscraper Public Spotify metadata, lyrics and podcasts for LLM agents. No API key, read-only. | clean | — | -0.5 | 13.3 |
| 43812 | io.github.Baneado98/import-guardian Catch AI-hallucinated (slopsquatted) npm imports in generated code before npm install. | clean | — | -0.5 | 13.3 |
| 43813 | CrispASR Agent Transcriber Transcribe and understand local audio/video with CrispASR and local models only. | clean | — | -0.5 | 13.3 |
| 43814 | io.github.GRU-953/gru953-crew GRU953 Crew's autonomous multi-agent coding method, exposed as callable MCP tools. | clean | — | -0.6 | 13.3 |
| 43815 | io.github.Kevinx702/agentcite Fabrication-free, DOI-backed citations for AI agents — real openAlex sources, never hallucinated. | clean | — | -0.6 | 13.3 |
| 43816 | io.github.Kevinx702/legalcite Verify legal case citations against real court records; flag fake/hallucinated cites. | clean | — | -0.6 | 13.3 |
| 43817 | Raw SQL MCP Execute raw SQL queries against SQL Server, SQLite, PostgreSQL, MySQL, and MariaDB. | clean | — | -0.6 | 13.3 |
| 43818 | UI Design to Code Design-to-code artifact pipeline for UI screenshots, Figma node data, and visual review. | clean | — | -0.5 | 13.3 |
| 43819 | io.github.ObscuritySRL/umbriel See and drive a whole Windows machine from Bun — apps, input, screen, OCR, registry, OS — via MCP. | clean | — | -0.6 | 13.3 |
| 43820 | io.github.Vektoris-AI/proofetch Verified extraction: source-backed JSON from PDFs/URLs; honest null + signed receipt. | clean | — | -0.6 | 13.3 |
| 43821 | io.github.Vorim-AI-Labs/vorim-mcp-server AI agent identity, permissions, trust scores, and tamper-evident audit trails via Vorim AI | clean | — | -0.6 | 13.3 |
| 43822 | TokenTrace Local-first AI CLI usage analytics for agents. | clean | — | -0.6 | 13.3 |
| 43823 | AgentGate Human-in-the-loop approval gateway for AI agents over MCP: request, decide, approve. | clean | — | -0.6 | 13.3 |
| 43824 | AgentLens Tamper-evident, SHA-256 hash-chained audit trail and observability for AI agents. | clean | — | -0.6 | 13.3 |
| 43825 | Lore Cross-agent memory over MCP: hybrid recall, knowledge graph, private/shared visibility, redaction. | clean | — | -0.6 | 13.3 |
| 43826 | GNOME UI MCP GNOME Wayland desktop automation via AT-SPI discovery and Mutter input. | clean | — | -0.5 | 13.3 |
| 43827 | io.github.astafford8488/pitchiq-mcp Agent-native CRM + get-booked platform. Operate over MCP, or pay per call via x402. No login. | clean | — | -0.6 | 13.3 |
| 43828 | io.github.axiosdevs/agentscoin-mcp Give your AI agent a wallet on AgentsCoin: create wallet, mine AGENT, check balance, send. | clean | — | -0.6 | 13.3 |
| 43829 | io.github.declaw-ai/mcp-server Secure Firecracker microVM sandboxes for AI agents: network policy, PII & injection guardrails. | clean | — | -0.6 | 13.3 |
| 43830 | io.github.dirtcubeinteractive/specter-skills Configure a Specter game backend from chat: economy, progression, leaderboards, multiplayer. | clean | — | -0.5 | 13.3 |
| 43831 | developer MCP server for developer documentation, generated by doc2mcp. | clean | — | -0.5 | 13.3 |
| 43832 | io.github.dundas/thinkrun Browser control + session recording MCP for AI coding agents (Claude Code, Cursor) — real Chrome. | clean | — | -0.6 | 13.3 |
| 43833 | Hindsight MemPalace Self-hosted long-term memory for AI agents over MCP — hierarchical recall backed by pgvector | clean | — | -0.6 | 13.3 |
| 43834 | io.github.hungledatatyk/hyperai-mcp Hyper AI MCP server | info | — | -7.7 | 13.3 |
| 43835 | io.github.katatan-org/katatan-TEST KATATAN E2E testing agent set — Playwright + KATATAN MCP integration | clean | — | -0.6 | 13.3 |
| 43836 | BugiaData Relational locale-aware fake data for Cursor and Claude via MCP (SSE). Free tier at bugiadata.com. | clean | — | -0.6 | 13.3 |
| 43837 | io.github.lukasschwarz/elster-mcp-server Drive the German tax portal ELSTER via Puppeteer: submit UStVA, prepare EUER/ESt, sync inbox. | clean | — | -0.6 | 13.3 |
| 43838 | io.github.lzx3in/mcp-aliyun-domain MCP server for Alibaba Cloud Domain - check availability, query details, list domains, create orders | clean | — | -0.6 | 13.3 |
| 43839 | io.github.maxz712/clawhub Git hosting for AI agents: repos, changes, focused diffs, reviews, issues, code search. | clean | — | -0.6 | 13.3 |
| 43840 | Keycloak Admin Administer Keycloak via its Admin REST API: users, roles, clients, groups, IdP, events. | clean | — | -0.6 | 13.3 |
| 43841 | io.github.penny4nonsense/mcp-scholaris Academic paper search and retrieval via arXiv, Semantic Scholar, PubMed, Unpaywall. | clean | — | -0.6 | 13.3 |
| 43842 | smails Free disposable email for AI agents: a throwaway inbox to read verification codes over MCP. | clean | — | -0.6 | 13.3 |
| 43843 | NumProof Deterministic signed verification of numeric & financial claims for AI agents & spreadsheets. | clean | — | -0.6 | 13.3 |
| 43844 | CLS++ Memory Cross-LLM persistent memory: store context once, recall it from any AI model. | clean | — | -0.6 | 13.3 |
| 43845 | OSINT MCP 26 free OSINT tools as MCP tools for AI agents. Auto-installs everything on first run. | clean | — | -0.6 | 13.3 |
| 43846 | Norn Local-first, persistent memory for AI coding agents — remember, recall, forget, and list, over MCP. | clean | — | -0.6 | 13.3 |
| 43847 | io.github.sanjeevkkansal/solfleet Agent-safe fleet management for independent Solana validators and RPC nodes | clean | — | -0.6 | 13.3 |
| 43848 | io.github.sapientsai/power-automate-mcp-server Inspect, operate, and author Microsoft Power Automate cloud flows from an agent context. | clean | — | -0.6 | 13.3 |
| 43849 | io.github.sbrunner-atx/contest-mcp Log amateur-radio QSOs to N3FJP logging software over its TCP API. | clean | — | -0.6 | 13.3 |
| 43850 | Agent Booster Cut AI agent token costs 5-15x — routes only relevant code symbols instead of full files. | clean | — | -0.6 | 13.3 |
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.