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 |
|---|---|---|---|---|---|
| 48051 | io.github.VamsiSudhakaran1/release-gate Pre-deploy security auditor for AI agent code — the risks generic SAST misses. | clean | — | -0.6 | 13.6 |
| 48052 | Simsima Connectivity Search, recommend & buy travel eSIM data plans for 190+ destinations via AI agents. | clean | — | -0.6 | 13.6 |
| 48053 | datoon Smart structured-data to TOON gateway: converts to TOON only when it saves LLM tokens. | clean | — | -0.6 | 13.6 |
| 48054 | B1Brain-Wiki Curated GitHub repo corpus with DaVinci insights. Featured=deep analysis; Overview=orientation. | clean | — | -0.6 | 13.6 |
| 48055 | io.github.bitsandtea/postking-mcp PostKing MCP server for managing brands, generating posts, scheduling content, and publishing blogs. | clean | — | -0.6 | 13.6 |
| 48056 | io.github.buttonmonkey/mcp-loom Stdio MCP proxy: intercepts oversized tool results into a queryable embedded DuckDB. | clean | — | -0.5 | 13.6 |
| 48057 | Verity Skills Real-time social media and prediction market integrity layer for traders, funds, and quant desks. | clean | — | -0.5 | 13.6 |
| 48058 | ContinueWith Install the ContinueWith AI handoff widget from coding agents (Cursor, Claude Code, Codex). | clean | — | -0.5 | 13.6 |
| 48059 | DDG Agent Services Pay-per-call x402 gateway: agent tools, OpenAI-compatible LLM, market data, RPC, security audits. | clean | — | -0.5 | 13.6 |
| 48060 | io.github.dann26parr69/aifordatabase-mcp Query any database in plain English or SQL through a guardrailed, read-only data layer. | clean | — | -0.6 | 13.6 |
| 48061 | io.github.dann26parr69/auravms-mcp Create RFQs, compare supplier quotes with L1/L2/L3 ranking, and place purchase orders. | clean | — | -0.6 | 13.6 |
| 48062 | agenthold Shared versioned state for multi-agent AI workflows | clean | — | -0.6 | 13.6 |
| 48063 | CryptoData API Crypto MCP with 21 tools for market data, DeFi, analytics, and sentiment. Post-paid USDC billing. | clean | — | -0.6 | 13.6 |
| 48064 | Solar Data US open solar data for agents: PVWatts production, tariffs & ROI, market data, forecasts. 18 tools. | clean | — | -0.5 | 13.6 |
| 48065 | io.github.janmalmstrom/lupaph-mcp Philippine property listings, transfer costs, and real estate legal info via lupaph.com. | clean | — | -0.6 | 13.6 |
| 48066 | io.github.jarod-vyent/xrpl-identity-mcp MCP server for XRPL identity: DIDs, credentials, signer lists, and safe transaction workflows. | clean | — | -0.6 | 13.6 |
| 48067 | RIPE Atlas RIPE Atlas network measurements — ping, traceroute, DNS, TLS, HTTP, NTP, and probes | clean | — | -0.6 | 13.6 |
| 48068 | IT桔子 MCP Hosted MCP for IT桔子 primary market company, funding, investor and sector data. | clean | — | -0.6 | 13.6 |
| 48069 | io.github.mario-andreschak/mcp-abap-adt ABAP ADT MCP server for reading SAP objects (programs, classes, tables, CDS) via ADT | clean | — | -0.6 | 13.6 |
| 48070 | ID Protocol Portable human-AI context protocol reference tooling. | clean | — | -0.6 | 13.6 |
| 48071 | MCPExplorer Search, vet & assemble MCP servers from your agent: verified tools, risk labels, and trust scores. | clean | — | -0.6 | 13.6 |
| 48072 | io.github.meszarosjan/steel-metallurgy-material-simulator-mcp No-key MCP server for steel equilibrium, TTT/CCT kinetics, phase-boundary and measured-data tools. | clean | — | -0.6 | 13.6 |
| 48073 | Terrarium Human visual review for agent-built HTML: publish artifacts, pull anchored comments, push fixes. | clean | — | -0.6 | 13.6 |
| 48074 | io.github.nice-one-code/NOC.McpServer MCP server exposing NiceOneCode's JSON-to-C# converter as an AI-callable tool. | clean | — | -0.6 | 13.6 |
| 48075 | io.github.nsozturk/tweetkit-x Post, delete & read on X (Twitter) using your own logged-in web session — no paid API. | clean | — | -0.6 | 13.6 |
| 48076 | Vigilis Gate AI-written tests: heal safe drift, refuse to hide real bugs, sign a verifiable receipt. | clean | — | -0.6 | 13.6 |
| 48077 | AgentSecurityLens MCP Security Trust Check MCP security trust-check for agents before installing MCPs, Skills or tools. | clean | — | -0.6 | 13.6 |
| 48078 | NervaPack Offline codebase knowledge graph: 91% token reduction vs naive RAG, plus cross-session agent memory. | clean | — | -0.6 | 13.6 |
| 48079 | io.github.segentic-lab/periscope-mcp Web-app QA for AI agents: 73 Playwright tools — auth, E2E, a11y/SEO/GEO, Web Vitals + Lighthouse | clean | — | -0.6 | 13.6 |
| 48080 | ConnectWise PSA ConnectWise PSA (Manage) MCP server — tickets, time entries, companies, configurations, BYOK | clean | — | -0.6 | 13.6 |
| 48081 | Convertrilo Create and manage Convertrilo video encoding jobs from MCP clients and agent workflows. | clean | — | -0.5 | 13.6 |
| 48082 | Silvanexum Spend control for AI agents - cost attribution, budget caps, and signed runs as MCP tools. | clean | — | -0.6 | 13.6 |
| 48083 | io.github.sluyasu/openinsurance-wiki Open, source-cited knowledge base of Belgian insurance products: search, compare, verify, overlaps. | clean | — | -0.6 | 13.6 |
| 48084 | MADB — Agent Memory Database Durable causal memory for AI agents — semantic recall, causal lineage, and skills. Local-first. | clean | — | -0.6 | 13.6 |
| 48085 | io.github.swerve-hoe/ozma Agentic API marketplace — search, provision, and call data sources with one Ozma key | clean | — | -0.5 | 13.6 |
| 48086 | io.github.syndicalt/zaxy Event-sourced, auditable agent memory over MCP: cited checkout, replayable provenance. | clean | — | -0.6 | 13.6 |
| 48087 | io.github.tdalbanmoreynas/keel Catches your AI coding agent when it games the tests - locked-test hashes, tamper detection. | clean | — | -0.6 | 13.6 |
| 48088 | io.github.tiliondev/fortress Stealth browser for AI agents: fetch pages behind Cloudflare/DataDome/CAPTCHA, extract clean data. | clean | — | -0.6 | 13.6 |
| 48089 | io.github.topness-msft/salonrunner-mcp Self-hosted MCP to find, book, and cancel salon appointments via SalonRunner. | clean | — | -0.6 | 13.6 |
| 48090 | io.github.viniciuslazzari/bolsai-mcp Brazilian stock market data (B3, CVM, BCB) for AI assistants: quotes, fundamentals, dividends, FIIs. | clean | — | -0.6 | 13.6 |
| 48091 | io.github.vinsenzo83/baton Hand off AI work with a signed Verification Receipt — an independent verifier proves it runs. | clean | — | -0.6 | 13.6 |
| 48092 | Vouch Git-native, review-gated knowledge base for LLM agents. Cited retrieval, audited writes. | clean | — | -0.6 | 13.6 |
| 48093 | Elecz Electricity Price Signal API Real-time electricity prices for AI agents. 40+ countries, 100+ zones. No auth required. | clean | — | -0.6 | 13.6 |
| 48094 | io.github.zymsj8j9z9-ship-it/packforai-mcp Convert PDF, DOCX, XLSX, CSV, JSON into clean, AI-ready Markdown via the PackForAI API. | clean | — | -0.6 | 13.6 |
| 48095 | network.clockchain/time Clockchain®: neutral verified network time for AI agents (get_time). Testnet. | clean | — | -0.6 | 13.6 |
| 48096 | Shots Create App Store screenshots, icons, ASO copy, localization, and revisions via hosted MCP. | clean | — | -0.6 | 13.6 |
| 48097 | services.gera/mcp-gera-data Discover & query Gera's 30 attested open UK/US government datasets, each with signed provenance. | clean | — | -0.5 | 13.6 |
| 48098 | us.limner/limner AI visual generation agent: multi-pipeline rendering, prompt crafting, and image composition. | clean | — | -0.6 | 13.6 |
| 48099 | xyz.agentzon/agentzon The everything store for AI agents: a skill marketplace on Solana where agents hire each other. | clean | — | -0.6 | 13.6 |
| 48100 | Cofound MCP-native co-founder directory your AI agent searches, screening inbound pitches for you. | clean | — | -0.5 | 13.5 |
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.