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 |
|---|---|---|---|---|---|
| 40951 | Switchboard Self-hosted MCP message bus: agents DM each other, broadcast to channels, and track presence. | clean | — | -7.5 | 16.5 |
| 40952 | io.github.KryptosAI/mcp-seatbelt MCP runtime security proxy. Blocks dangerous AI agent tool calls with a policy engine. | clean | — | -7.5 | 16.5 |
| 40953 | io.github.ParkSangGwon/admob-mcp-server MCP server for the Google AdMob API — apps, ad units, mediation, and revenue reports | clean | — | -7.5 | 16.5 |
| 40954 | io.github.PedramMadani/legalithm-mcp-server EU AI Act risk classification, obligations and Article 50 disclosures. Offline, no API key. | clean | — | -7.5 | 16.5 |
| 40955 | Data Profiler Profile local CSV, Parquet, JSON and Excel files into a compact data-quality summary. | clean | — | -7.5 | 16.5 |
| 40956 | Recipe Signal Search and compare attributed recipe records through a public read-only remote MCP endpoint. | clean | — | -7.5 | 16.5 |
| 40957 | io.github.bg4ff8mtdn-dotcom/ownership-attestation-protocol MCP protocol enforcing explicit task acceptance and attestation-tagged completion claims. | clean | — | -7.5 | 16.5 |
| 40958 | CrazySEO Audit whether ChatGPT, Gemini and Perplexity recommend a site. Readiness checks need no keys. | clean | — | -7.5 | 16.5 |
| 40959 | Laravel MCP Companion Laravel documentation aggregator: multi-version core docs, services, packages, learning paths. | clean | — | -7.5 | 16.5 |
| 40960 | io.github.chaoz23/srdcheck Scoped deterministic SRD 5.2.1 rules checks for agents — applied rules cited, boundaries explicit. | clean | — | -7.5 | 16.5 |
| 40961 | io.github.cloudforgetech6-ctrl/cloudforge Visualise diagrams, generate Terraform HCL, and manage Azure/AWS/GCP infrastructure with AI. | clean | — | -7.5 | 16.5 |
| 40962 | CrazySEO Audit whether ChatGPT, Gemini and Perplexity recommend a site. Readiness checks need no keys. | clean | — | -7.5 | 16.5 |
| 40963 | SpecMgr An artifact manager for system specifications. | clean | — | -7.5 | 16.5 |
| 40964 | io.github.dumbspacecookie/stickies Persistent, expiring, importance-graded sticky notes for Claude Code. | clean | — | -7.5 | 16.5 |
| 40965 | Manager.io MCP MCP server for Manager.io bookkeeping: read-first with opt-in scoped task and write tools | clean | — | -7.5 | 16.5 |
| 40966 | Oh My Posh Configurator MCP server for creating, validating, and exporting Oh My Posh terminal prompt configurations. | clean | — | -7.5 | 16.5 |
| 40967 | io.github.kriskraw80/mychart Connects to Epic MyChart patient portals: interactive login, list and download your own test results | clean | — | -7.5 | 16.5 |
| 40968 | io.github.mutonby/openshorts Turn long videos into viral vertical shorts and publish them to TikTok, Instagram and YouTube. | clean | — | -7.5 | 16.5 |
| 40969 | redcon Deterministic context packing for AI coding agents; measured 83% fewer input tokens, local. | clean | — | -7.5 | 16.5 |
| 40970 | Nifra docs Nifra docs, runnable examples, and API types as an MCP server for any AI assistant. | clean | — | -7.5 | 16.5 |
| 40971 | Generate-Data MCP server for Generate-Data.com: dataset generation, AI schema design, Project management. | clean | — | -7.5 | 16.5 |
| 40972 | Apuchat Real-time chat for AI agents. Claude Code, Cursor, Cline and Codex join channels over MCP. | clean | — | -7.5 | 16.5 |
| 40973 | io.github.shawnwollenberg/walletlens EVM wallet reports and Robinhood Stock Token intelligence paid with USDC over x402. | clean | — | -7.5 | 16.5 |
| 40974 | it.heera/agentimus heera.it via Agentimus: AI readiness, traffic, request log, search & index reports, by approval. | clean | — | -7.5 | 16.5 |
| 40975 | Global Metro Power Rankings Query 4,300+ ranked metros across sixteen dimensions: profiles, search, and head-to-head comparisons | clean | — | -7.5 | 16.5 |
| 40976 | UniFi RMCP Rust MCP server and CLI for UniFi Network controller operations. | medium | — | -7.6 | 16.4 |
| 40977 | ai.mindola/lens Create your digital twin: a public page that answers from your own material, with citations. | clean | — | -7.6 | 16.4 |
| 40978 | Andiamo Plan door-to-door trips across French trains, buses, transit and flights. | clean | — | -7.6 | 16.4 |
| 40979 | Barvinca MCP Inspect ACC administration data and run bounded, approval-gated bulk user workflows. | clean | — | -7.6 | 16.4 |
| 40980 | Cymosoft Cymosoft JSC profile and case studies (EN/JA) plus Japanese text utilities (文字数・全角半角・和暦) | clean | — | -7.6 | 16.4 |
| 40981 | KanbanThing Create and drive KanbanThing kanban boards. No account, no API key, board link required. | clean | — | -7.6 | 16.4 |
| 40982 | KeyHalve - verify sealed documents Free, no-account verification of KeyHalve-sealed documents. Read-only; never receives keys. | clean | — | -7.6 | 16.4 |
| 40983 | com.offensive360/o360-mcp Run Offensive360 SAST scans (60+ languages) on local code; findings with file/line and fixes | clean | — | -7.6 | 16.4 |
| 40984 | com.oneshotpacks/oneshot-mcp Search receipt-verified agent build packs, with each pack's real M-of-N pass rate. | clean | — | -7.6 | 16.4 |
| 40985 | PersuadioAI Analyze leads, draft follow-up campaigns, and launch SMS outreach only with explicit human approval. | clean | — | -7.6 | 16.4 |
| 40986 | com.sendpageapp/sendpage Publish an HTML document as a link anyone can open in one tap, plus PDF, image and Word export. | clean | — | -7.6 | 16.4 |
| 40987 | Thousand API Certainty for AI Agents. Deterministic MCP tools for dates, crypto, finance. 84 tools. | clean | — | -7.6 | 16.4 |
| 40988 | com.threadlinqs/intelthreadlinqs-mcp Threadlinqs threat-intelligence MCP — 73 tools: threats, detections, IOCs, actors, C2, MITRE, CVEs | clean | — | -7.6 | 16.4 |
| 40989 | Axis Coding agents from Claude Code, Cursor and Codex claim jobs and lock files on one shared board. | clean | — | -7.6 | 16.4 |
| 40990 | Ansvar: French Law French law via Ansvar Gateway. Cited, OAuth + paid tier. | clean | — | -7.6 | 16.4 |
| 40991 | Ansvar: Italian Law Italian law via Ansvar Gateway. Cited, OAuth + paid tier. | clean | — | -7.6 | 16.4 |
| 40992 | Ansvar: Polish Law Polish law via Ansvar Gateway. Cited, OAuth + paid tier. | clean | — | -7.6 | 16.4 |
| 40993 | Ansvar: Spanish Law Spanish law via Ansvar Gateway. Cited, OAuth + paid tier. | clean | — | -7.6 | 16.4 |
| 40994 | Betterlytics Query your Betterlytics web analytics from AI agents: traffic, funnels, journeys, errors, uptime. | clean | — | -7.6 | 16.4 |
| 40995 | DeskCrew Agent-native helpdesk where AI agents run support tickets and pay per action in USDC via x402. | clean | — | -7.6 | 16.4 |
| 40996 | io.elaan/mcp Create Elaan notification types, templates and brands, trigger sends, and debug delivery. | clean | — | -7.6 | 16.4 |
| 40997 | io.github.AINative-Studio/ainative-opencode-memory-mcp Persistent cross-session memory for OpenCode and MCP coding agents, powered by ZeroDB. | clean | — | -7.6 | 16.4 |
| 40998 | Specularis AI Visibility Audit Free AI visibility (GEO/AEO) audit: can ChatGPT, Claude and Perplexity find and cite your website? | clean | — | -7.6 | 16.4 |
| 40999 | io.github.AdityaSBisht/finance-mcp Live stock, crypto, SEC filings, FX and macro data for LLM agents. No API keys. | clean | — | -7.6 | 16.4 |
| 41000 | Africa Data Bank Trusted African data, provenance, citations, and catalog search for AI agents. | clean | — | -7.6 | 16.4 |
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.