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 |
|---|---|---|---|---|---|
| 54801 | io.github.asume21/webear Give your AI coding assistant ears — capture, analyze, and describe live audio. | clean | — | — | 9.0 |
| 54802 | io.github.ataberk-xyz/gossipcat Multi-agent orchestration for Claude Code — consensus review, adaptive dispatch, skill learning | medium | — | — | 9.0 |
| 54803 | io.github.atakanelik34/neo-x402-mcp 8-tool AI web intelligence suite: search, scrape, screenshot, SEO, docs, crypto, code. | clean | — | — | 9.0 |
| 54804 | io.github.atarkowska/fastmcp-pdftools An MCP server that provides [describe what your server does] | clean | — | — | 9.0 |
| 54805 | io.github.atarkowska/fastmcp-sqltools A MCP server provides SQL database access with support for PostgreSQL, MySQL, and SQLite. | clean | — | — | 9.0 |
| 54806 | io.github.atk1-eng/weather An MCP server for weather information. | clean | — | — | 9.0 |
| 54807 | io.github.atmflow55/datafood-mcp DataFood: 16 data sources (crypto/DeFi/security/news/finance) via one MCP. Bundles save ~92%. | clean | — | — | 9.0 |
| 54808 | io.github.atul-fusionpact/fusionpact-vectordb Hybrid vector + reasoning retrieval, agent memory, multi-agent orchestration, MCP server, and RAG. | clean | — | — | 9.0 |
| 54809 | ATXP — Agent Payment & Wallet Infrastructure Agent wallet, email, phone, and 41 paid tools: search, image/video/music gen, SMS, calls. | clean | — | — | 9.0 |
| 54810 | io.github.augee99/mcp-weather An MCP server that provides [describe what your server does] | clean | — | — | 9.0 |
| 54811 | VARRD — Statistically Validated Trading Edges + AI Research Engine Validated trading edges across futures, equities, crypto. Live signals, full audit trail. | clean | — | — | 9.0 |
| 54812 | io.github.augmnt/augments-mcp-server Augments MCP Server - A comprehensive framework documentation provider for Claude Code | clean | — | — | 9.0 |
| 54813 | io.github.aurekai/aurekai-mcp Aurekai MCP server for akai doctor, manifests, artifacts, feature queries, and runtime inspection. | clean | — | — | 9.0 |
| 54814 | io.github.auroracapital/claude-ops-telegram-server Telegram personal-account MCP (MTProto user-auth). Read DMs, send messages, search across chats. | clean | — | — | 9.0 |
| 54815 | io.github.austenstone/myinstants Give your AI agent a soundboard. Millions of meme sounds from myinstants.com. | clean | — | — | 9.0 |
| 54816 | io.github.austenstone/myinstants-mcp Give your AI agent a soundboard. Millions of meme sounds from myinstants.com. | clean | — | — | 9.0 |
| 54817 | io.github.avclabs/enhance-mcp HTTP MCP Client-Server for video enhancement API | clean | — | — | 9.0 |
| 54818 | io.github.avclabs/media-mcp MCP Server for video enhancement and image segmentation (SAM3) | clean | — | -0.5 | 9.0 |
| 54819 | MCP Server for OSCAL AI agent tools for Open Security Controls Assessment Language (OSCAL) | clean | — | — | 9.0 |
| 54820 | Terminal MCP Server MCP server for AI agents to interact with terminal applications. Think Playwright for terminals. | clean | — | — | 9.0 |
| 54821 | Path402 — Tokenised Web Content for AI Agents AI agents discover, acquire, and re-serve tokenised web content via the $402 protocol | clean | — | — | 9.0 |
| 54822 | io.github.babelwrap/babelwrap-mcp MCP server for BabelWrap — give AI agents web browsing superpowers. | clean | — | — | 9.0 |
| 54823 | io.github.backspacevenkat/perspectives Query GPT 5.2, Claude Opus 4.5, Gemini 3, Grok 4.1 simultaneously for AI perspectives | clean | — | — | 9.0 |
| 54824 | io.github.bahfahh/noteit-mcp MCP server for AI agent profiles and smart notes. 60+ coding prompt packs with expert personas. | clean | — | — | 9.0 |
| 54825 | io.github.baixianger/camoufox-mcp Anti-detection browser automation with Camoufox - stealth Firefox for web scraping | clean | — | — | 9.0 |
| 54826 | io.github.baixianger/langchain-mcp LangChain/LangGraph/DeepAgents knowledge + LangGraph agent debugging (Polly-like) | clean | — | — | 9.0 |
| 54827 | io.github.bajoski34/mcp-flutterwave MCP Server to interact with Flutterwave APIs. | clean | — | — | 9.0 |
| 54828 | io.github.bamchi/scrapi Web scraping for AI agents. Converts URLs to clean, LLM-ready Markdown with anti-bot bypass. | clean | — | — | 9.0 |
| 54829 | io.github.baronsengir007/openclaw-agent-tools Weather, code search, currency & Solana trust scoring as MCP tools. Free, no API key needed. | clean | — | — | 9.0 |
| 54830 | OpenClaw Trust Scorer Solana wallet trust scoring: tier, tx count, balance, liveness. | clean | — | — | 9.0 |
| 54831 | io.github.basalt-run/basalt Design tokens, components, icons, and a11y data via MCP. For Cursor, Claude, and Windsurf. | clean | — | — | 9.0 |
| 54832 | io.github.base76-research-lab/cognos-session-memory CognOS trust scoring (C=p·(1-Ue-Ua)) and session trace storage as MCP tools. | clean | — | — | 9.0 |
| 54833 | io.github.base76-research-lab/conductor-graph-mcp Exposes a CognOS agent system as a machine-readable graph. Full system snapshot with one tool call. | clean | — | — | 9.0 |
| 54834 | io.github.base76-research-lab/token-compressor Compress prompts 40-60% using local LLM + embedding validation. Preserves all conditionals. | clean | — | — | 9.0 |
| 54835 | Forums Ask any GitHub repository a question. Get source-backed answers. | clean | — | — | 9.0 |
| 54836 | io.github.batook22/project-knowledge-mcp Cross-project knowledge graph for MCP — map features across mobile, backend, and admin codebases. | clean | — | -0.2 | 9.0 |
| 54837 | io.github.bats64mgutsi/nextrole-mcp-proxy MCP proxy server for NextRole CV tailoring services | clean | — | — | 9.0 |
| 54838 | Bawbel Scanner Security scanner for MCP servers and skill files. Detects AVE vulnerabilities before production. | clean | — | — | 9.0 |
| 54839 | CodeMap Roslyn-powered MCP server for C#/VB.NET. Query symbols, call graphs, and facts. 90%+ token savings. | clean | — | — | 9.0 |
| 54840 | io.github.bbb-build/mascope-mcp World MiniApp reviews and analytics — verified human ratings via World ID | clean | — | — | 9.0 |
| 54841 | io.github.bbb-build/touchgrass-mcp Hire Orb-verified humans for real-world tasks with on-chain escrow on World Chain | clean | — | — | 9.0 |
| 54842 | MoltAwards Federal + state government contracts, awards, jobs, and B2B subcontracting for AI agents. | clean | — | — | 9.0 |
| 54843 | io.github.bch1212/agent-commerce-mcp Agent Commerce MCP — agent-native A2A storefront. Discovery, Stripe checkout, affiliate program. | clean | — | -0.6 | 9.0 |
| 54844 | io.github.bch1212/agentfetch Token-budgeted web fetch for AI agents — auto-routes Jina, FireCrawl, Trafilatura, PDF. | clean | — | — | 9.0 |
| 54845 | io.github.bch1212/agenttrust Trust scores & reputation for the agent-to-agent economy. Verify A2A counterparties. | clean | — | -0.6 | 9.0 |
| 54846 | io.github.bch1212/agentvault Credential vault for AI agents — Fernet-encrypted keys, per-agent budgets, audit logs. | clean | — | -0.6 | 9.0 |
| 54847 | io.github.bch1212/bizintel Local business intel for AI agents: audits, lead scoring, tech stack, prospecting. | clean | — | -0.3 | 9.0 |
| 54848 | io.github.bch1212/injectshield Prompt-injection firewall for AI agents — scan untrusted text before LLM calls. | clean | — | — | 9.0 |
| 54849 | io.github.bch1212/outdooriq-mcp Paid MCP for fishing/lake/stocking intelligence — 72k+ US lakes, 293k+ events. | clean | — | -0.3 | 9.0 |
| 54850 | io.github.bch1212/pubrecords US public-records intelligence for AI agents — companies, SEC, courts, spending, licenses. | clean | — | -0.3 | 9.0 |
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.