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.

45,870
servers indexed
87
with verified activity
20.0
median score
15,176
carrying risk flags
last refreshed

Leaderboard

Activity & maintenance, not security — how this is scored
MCP servers ranked by activity and maintenance score, highest first.
#ServerFlagsStarsChangeScore
7601io.github.ascanioUnderIndex/underindex
Verified records on 60 niche fashion subcultures for AI agents, $0.01 per lookup over x402
clean——
24.0
7602AsDecided
Read-only access to deterministic engineering decisions stored in a local repository.
clean——
24.0
7603opchain
Claude Code / MCP skills for the dev pipeline: discover, spec, design, build, ship, operate.
clean——
24.0
7604KarmaDue
Pre-install safety check for agents: known traps, tested fixes, malware reports. No account.
clean—+4.0
24.0
7605rpt-mcp (SAP Crystal Reports)
Inspect and edit SAP Crystal Reports .rpt files (Windows; needs the Crystal runtime).
clean——
24.0
7606verify-atom
Signed proof of web observations for AI agents: Ed25519 proof packets for any URL.
clean——
24.0
7607Kshana PNT-resilience simulator
Validated Kshana PNT simulator: orbits, GNSS, fusion, receiver trust, interference maps.
clean——
24.0
7608ReplyAtlas
Manage Instagram comment-to-DM automations, leads, analytics, conversations and broadcasts.
clean——
24.0
7609vaultguard
AI agents use your Obsidian secrets by name — values never reach their context.
clean——
24.0
7610io.github.ashishsinha1602/schemagate
Identity-scoped schema selection for text-to-SQL. Returns only the tables the caller may read.
clean——
24.0
7611Lexicon
Fixes the names and jargon speech-to-text gets wrong before your agent acts on a dictated prompt.
clean——
24.0
7612Phantom Secrets
Value-blind secret metadata and gated workflows for AI coding agents through Phantom's local proxy.
medium——
24.0
7613Spoor
What changed across metrics, logs and traces, and where it started (VictoriaMetrics stack).
clean——
24.0
7614Agent Readiness Auditor
Audits any website for AI agent readiness and safety, scoring prompt injection risk and llms.txt.
clean——
24.0
7615VK Ads MCP
MCP server for VK Ads (VK Реклама) API: manage ad plans, ad groups, banners, and statistics.
clean——
24.0
7616Yandex Direct MCP
MCP server for Yandex Direct API v5: manage PPC campaigns, ads, keywords, and statistics.
clean——
24.0
7617Yandex Metrica MCP
MCP server for Yandex Metrica API: list counters, goals and pull web-analytics statistics.
clean——
24.0
7618Yandex Webmaster MCP
MCP server for Yandex Webmaster API: indexing, search queries, sitemaps, diagnostics, links.
clean——
24.0
7619Yandex Wordstat MCP
MCP server for Yandex Wordstat API: top & related queries, demand dynamics and regions.
clean——
24.0
7620io.github.asklokesh/loki-mode
Autonomous spec-to-product coding-agent CLI with an MCP server exposing 39 tools over stdio.
clean——
24.0
7621AskMarcel HVAC Technical Knowledge
15 HVAC MCP tools: lookups, SKU provenance, guided PAC, Beta Harness sessions. 126 brands.
clean——
24.0
7622Generate Tech Stack
Visual tech-stack inventory of any codebase: languages, frameworks, databases, AI SDKs, infra.
clean——
24.0
7623Workflow Generator
Architecture diagram with concurrency capacity and bottleneck estimates from any codebase.
clean——
24.0
7624StatCite — Verified Economic Statistics
Cited economic statistics: World Bank, IMF, BIS, ECB, Caribbean central banks. Verify any figure.
clean——
24.0
7625Global Executables
Check whether a CLI command name is already taken across npm, PyPI, crates.io, Go, Debian and more
clean——
24.0
7626FTX MCP — FactoryTalk Optix MCP Server
MCP server for FactoryTalk Optix: author, preview, and verify Studio changes via the emulator.
clean——
24.0
7627io.github.asr-aditya/iconserve
Icons for agentic development: search & fetch 366,000+ open-source icons as SVG/PNG. No API key.
clean——
24.0
7628Expense
Receipt tracker with no friction: receipts arrive by email and file themselves
clean——
24.0
7629io.github.assafbar2/agentswitchboard
Search a curated directory of 300+ verified AI agents, MCP servers, and agentic tools.
clean——
24.0
7630io.github.assafbar2/barnir-hired
Role guidance for technical go-to-market job fit (SA, CSM, SE, TAM, Support, FDE).
clean——
24.0
7631io.github.asselwan/twothumbs
Verifies AI agent work end to end: real artifacts and outcomes checked, not self-reported success.
clean——
24.0
7632AssetFare
Exact-amount top-two routing for six pilots; caller signs; AssetFare never signs or submits
clean——
24.0
7633AssetFare USDC Bridge
Exact-amount top-two routing for six pilots; caller signs; AssetFare never signs or submits
clean——
24.0
7634Jueban · Buddhist Companion
Read-only Buddhist scripture search, verified explanations, situation matching, and practice.
clean——
24.0
7635Assinafy
Send documents for legally valid e-signature in Brazil, track signers and download signed files.
clean——
24.0
7636Local YDB MCP
Operate local-ydb deployments through local or SSH-backed MCP tools.
clean——
24.0
7637io.github.astra-intelligence/web2md
Convert any URL to clean Markdown. Free tier: 10/day. Unlimited via Gumroad license.
clean——
24.0
7638Web2MD MCP Server
Convert any public URL to clean, readable Markdown for AI agents. Strips ads, navigation, and boi...
clean——
24.0
7639tsbootstrap
Read-only time-series bootstrap server: diagnose a series and compute confidence intervals.
clean——
24.0
7640Agentic House Search
UK neighbourhood research from government open data: postcode reports, comparisons, 45 datasets.
clean——
24.0
7641Papyrio PDF Tools
Compress, convert, merge, split and OCR PDFs from an assistant, using local files.
clean——
24.0
7642Bilinc
Hosted agent memory with provenance, contradiction surfacing, and snapshot rollback.
clean——
24.0
7643Clawifi
Agent-native internet gateway: typed search, fetch, scrape, crawl, and extract via the Clawifi API.
clean——
24.0
7644Sheets MCP
Google Sheets for agent workflows in Claude Code and Claude Desktop: APIs, files, schedules, undo.
clean——
24.0
7645io.github.atef-ataya/depwire
Dependency graph + 24 MCP tools. Impact analysis, simulation, security, agent coordination
clean——
24.0
7646Oh My Android
AI agents see and drive the Android Emulator: screenshots, UI in dp, tap, dark mode, RTL, logcat.
clean——
24.0
7647Agentic Target Evidence
Read-only biomedical evidence tools for drug-target validation: DepMap, gnomAD, OpenTargets, PubMed…
clean——
24.0
7648TradingMCP
Market analysis for AI assistants: screeners, multi-timeframe analysis, backtests, in-chat charts.
clean——
24.0
7649io.github.atlas26onchain/atlas-mcp
Base token safety checks (honeypot test, liquidity, new launches), paid per call in USDC via x402.
clean——
24.0
7650io.github.atlasbyauro/atlas-fda
FDA 510(k)s, PMAs, recalls & trials, linked: predicate search and review-time stats for AI agents.
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.