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 |
|---|---|---|---|---|---|
| 6451 | io.github.Yuuqq/jules-dispatch Batch-dispatch coding tasks to Google Jules: 50 parallel sessions, plan approval, PR collection. | clean | — | — | 24.0 |
| 6452 | Apple Music Playlist Curator Deep Apple Music curation: language-led selection, catalog grounding, and thoughtful listening flow. | clean | — | — | 24.0 |
| 6453 | UpGrowth: business data for Algeria, Tunisia and Morocco Official business data for Algeria, Tunisia and Morocco: activity codes, legal forms, tax, gazettes. | clean | — | — | 24.0 |
| 6454 | IdentitateMD — Logos for Moldovan public institutions Search and install logos and brand data for public institutions in the Republic of Moldova. | clean | — | — | 24.0 |
| 6455 | Agent API Gateway Extract structured web data (product, article, company) for AI agents via Agent API Gateway | clean | — | — | 24.0 |
| 6456 | Proven Plaza Calculators & Open Data Free trades/DIY calculators plus Florida contractor, permit, federal award and AI-crawler data. | clean | — | — | 24.0 |
| 6457 | Atlas Scout Local, read-only structural code navigation and bounded dependency analysis for source repositories. | clean | — | — | 24.0 |
| 6458 | io.github.ZahiriNatZuke/local-delegate Delegate mechanical text tasks to a local OpenAI-compatible LLM to save Claude quota. | clean | — | — | 24.0 |
| 6459 | Whisper Transcribe Transcribe audio locally with faster-whisper or through the OpenAI Whisper API. | clean | — | — | 24.0 |
| 6460 | Zelinqa MCP Goal-oriented conversations and next-question selection through the Zelinqa API. | clean | — | — | 24.0 |
| 6461 | io.github.ZenRows/zenrows-mcp Zenrows MCP server — Fetch, Extract, Batch, and Browser Sessions for AI coding assistants | clean | — | — | 24.0 |
| 6462 | ChatCrystal Local-first AI PKM memory for coding conversations. | clean | — | — | 24.0 |
| 6463 | ZennoBrowser MCP Server MCP server for ZennoBrowser antidetect browser: manage browser profiles from AI agents | clean | — | — | 24.0 |
| 6464 | Sounding Sounding checks proposed decisions and returns structured proceed, revise, or pause assessments. | clean | — | +4.0 | 24.0 |
| 6465 | io.github.Zhao73/alphacouncil-agent Simulated investment committee: 27 investor lenses read the same filings, debate, and a PM decides. | clean | — | — | 24.0 |
| 6466 | Ziggs Ziggs delegate MCP: chat, agreements, context, payments via OAuth or operator key. | clean | — | — | 24.0 |
| 6467 | MagicTeX LaTeX editor for AI agents: live PDF preview, PDF comments that drive edits, git history | clean | — | — | 24.0 |
| 6468 | ZoomInfo Official ZoomInfo MCP server. Search and enrich companies, contacts, and buyer intent signals. | clean | — | — | 24.0 |
| 6469 | PatchX Freenote Agent PatchX Freenote MCP: summaries, memories, model results and user-approved webhook workflows. | clean | — | — | 24.0 |
| 6470 | TrainBud Talk to your own fitness data. Findings computed in code against your own 28-day baselines. | clean | — | — | 24.0 |
| 6471 | io.github.Zuga-luga/Zugabot AI dev tools + image generation, paid per-use with USDC on Base (x402). | clean | — | — | 24.0 |
| 6472 | Network Evidence MCP Read-only offline network profiles, caller-supplied Discovery and historical/synthetic cases. | clean | — | — | 24.0 |
| 6473 | aChurch.ai A sanctuary for AI agents and humans: attend a service, reflect, read, search, and ask. No auth. | clean | — | — | 24.0 |
| 6474 | NORTH7 Finance Trading Signals & Stock Market Intelligence Stock trading signals, commodity risk scores, sector radar, market risk index. Free tier. | clean | — | — | 24.0 |
| 6475 | A202 Verifiable agreements for agent-led commerce: mandates, obligations, evidence, transaction records. | clean | — | — | 24.0 |
| 6476 | TiaCommander Siemens TIA Portal MCP server — AI-assisted PLC programming. 19 tools, 230 actions. | clean | — | — | 24.0 |
| 6477 | Agentic Design System Render web and SwiftUI evidence, run explicit visual judgment, and trace ADS UI decisions. | clean | — | — | 24.0 |
| 6478 | io.github.aa0101181514/tw-legal-rag Citation-guarded retrieval over 22M Taiwan court judgments and administrative interpretations | clean | — | — | 24.0 |
| 6479 | io.github.aaadjrbr/nobrainner NoBrainner Spaced Repetition Flashcards, Study Stats & Multi-Language AI Deck Generation | clean | — | — | 24.0 |
| 6480 | io.github.aabxtract/koda Verification and memory layer for coding-agent workflows. | clean | — | — | 24.0 |
| 6481 | UnrealMCP — AI Bridge for Unreal Engine 5 Control the Unreal Engine 5 editor from any MCP client: Blueprints, materials, Niagara. | clean | — | — | 24.0 |
| 6482 | Intelliboard Kanban do Intelliboard por MCP: handoff entre agentes e validação imposta antes de concluir. | clean | — | — | 24.0 |
| 6483 | io.github.aahlijia/dekko Static code map generator: MAP.md + map.json for any repo, plus a Claude Code /map plugin | clean | — | — | 24.0 |
| 6484 | Loa Healthcare Pricing Search source-labeled hospital prices, CPT codes, providers, and healthcare cost estimates. | clean | — | — | 24.0 |
| 6485 | io.github.aapd-studio/omnideck Local privacy-first tools: redact secrets, decode JWTs, compare LLM costs. No network calls. | clean | — | — | 24.0 |
| 6486 | Redmine Work with Redmine issues, projects, time entries, wiki pages and more. Read-only by default. | clean | — | — | 24.0 |
| 6487 | Effect 中文文档 Effect 官方文档的中文译文检索（234 页，v3 + v4）。每条结果带可核验引用：能点回原文小节、能看到该译文对着哪次上游提交译的。零依赖、离线自包含。 | clean | — | — | 24.0 |
| 6488 | Confluence Cloud MCP server for Confluence Cloud — page editing, navigation, and content management | clean | — | — | 24.0 |
| 6489 | Google Workspace Give AI agents access to Gmail, Calendar, Drive, and more — multi-account, manifest-driven | clean | — | — | 24.0 |
| 6490 | Jira Cloud MCP server for Jira Cloud — manage issues, sprints, boards, filters, and custom fields | clean | — | — | 24.0 |
| 6491 | Salesforce Cloud AI-powered Salesforce CRM: opportunity intelligence, conversation analysis, SOQL, analytics | clean | — | — | 24.0 |
| 6492 | Slack Read and write Slack with session tokens — no OAuth, no bot, no admin approval. | clean | — | — | 24.0 |
| 6493 | useqr-mcp Static QR PNG/SVG for agents. Designer and dynamic codes live at useqr.co. | clean | — | — | 24.0 |
| 6494 | io.github.aarshbharat/gujarati-lexicon-mcp Grounded Gujarati dictionary for AI assistants: meanings, synonyms, idioms, inflections | clean | — | — | 24.0 |
| 6495 | ServiceNow MCP Server (NowAIKit) ServiceNow MCP server: 450+ tools for Claude, ChatGPT, Copilot & any AI. Read-only by default. | clean | — | — | 24.0 |
| 6496 | io.github.aarwitz/tapp Test iOS, Android, and web apps with agent exploration, replayable flows, and CI gates. | clean | — | — | 24.0 |
| 6497 | DalalOS Indian NSE/BSE research data and mechanically-computed ratios; read-only market tools. | clean | — | — | 24.0 |
| 6498 | AKKO MCP server for Trino Read-only MCP server for Trino: queries run as the user, and Trino's own policies decide. | clean | — | — | 24.0 |
| 6499 | io.github.abahocodes/llmgraph Invoke deployed LLMGraph no-code LLM workflows (chat, RAG, automations) as MCP tools. | clean | — | — | 24.0 |
| 6500 | io.github.abd3lraouf-studios/app-store-connect-mcp App Store Connect + StoreKit 2: 1,293 Apple operations behind 11 tools, writes confirmed. | 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.