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 |
|---|---|---|---|---|---|
| 3301 | io.getsphere/sphere Log meals, check calories and macros, set up a nutrition plan, and search foods. | clean | — | — | 24.0 |
| 3302 | io.getunleash/unleash-mcp MCP server for managing Unleash feature flags | clean | — | — | 24.0 |
| 3303 | io.gildara/mcp-server Operating contracts for AI agents. Structured instructions compiled into system prompts. | clean | — | — | 24.0 |
| 3304 | GingerLive GingerLive livestream ad formats, network reach stats, campaign case studies, and streamer program. | clean | — | — | 24.0 |
| 3305 | Base Transaction Decoder Decode any Base tx: plain English, strict JSON, risk flags, no LLM. 50 free/day per IP, then $0.02. | clean | — | — | 24.0 |
| 3306 | io.github.0Mattias/bettermemory Memory for coding agents, checked against the filesystem and git before it is believed. | clean | — | — | 24.0 |
| 3307 | AINDF Read-only MCP server for one AINDF design-system bundle: look up what it offers, validate screens. | clean | — | — | 24.0 |
| 3308 | ui-ticket-mcp Human-to-AI code review bridge. Review UI in the browser, AI agents fix code via MCP. | clean | — | — | 24.0 |
| 3309 | io.github.0rkz/byte-protocol PayPerByte — per-byte data for AI agents: x402 USDC on Base, EIP-712-attested. No token. | clean | — | — | 24.0 |
| 3310 | Klarion Secret scanning for AI agents: rules and entropy find candidates, a model decides which are real. | clean | — | — | 24.0 |
| 3311 | Conceptio Search Search 1M+ open-access papers, standards, and case law from an AI agent. | clean | — | — | 24.0 |
| 3312 | Phishunt Public phishing feed: suspicious/confirmed phishing URLs detected hourly. No auth, CC0. | clean | — | — | 24.0 |
| 3313 | TweetFeed IOCs (URLs, domains, IPs, hashes) shared by the infosec community on X/Twitter. No auth, CC0. | clean | — | — | 24.0 |
| 3314 | AI Proof of Us Private signed AI task receipts with replay checks and optional validated AIPOU claims. | clean | — | — | 24.0 |
| 3315 | Sui Analytics Read-only Sui analytics: fund tracing, protocol-aware tx decoding, no API keys or wallet. | clean | — | — | 24.0 |
| 3316 | 0xinsider Read-only Polymarket sports and esports data: wallet grades on settled P&L, large trades, markets. | clean | — | — | 24.0 |
| 3317 | VaultVision Hyperliquid Vault Research Read-only Hyperliquid vault search, risk, drawdown, rankings, TVL, alerts, and comparisons. | clean | — | — | 24.0 |
| 3318 | io.github.0xmortuex/acpi-mcp Read ACPI tables from a live QEMU guest or files and explain them for OS developers. | clean | — | — | 24.0 |
| 3319 | io.github.0xmortuex/gdbstub-mcp Debug kernels through QEMU's gdbstub with no gdb binary - and explain triple faults. | clean | — | — | 24.0 |
| 3320 | io.github.0xmortuex/kconfig-mcp Why can't I enable CONFIG_X? Explains Kconfig dependencies and finds a verified fix. | clean | — | — | 24.0 |
| 3321 | io.github.0xmortuex/mort-mcp Write, type-check and run Mort code, with language spec and stdlib lookup. | clean | — | — | 24.0 |
| 3322 | io.github.0xmortuex/osdev-wiki-mcp The OSDev wiki (wiki.osdev.org) offline and searchable: search, sections, links. | clean | — | — | 24.0 |
| 3323 | io.github.0xsims/rubric-mcp Attested evidence tools for AI agents: sanctions screening, agent/wallet records, paid via x402. | clean | — | — | 24.0 |
| 3324 | io.github.0xsims/rubric-mcp-server Attest agent decisions and verify records on a public ledger. Evidence, not just data. | clean | — | — | 24.0 |
| 3325 | Cerebrus Pulse MCP Real-time Hyperliquid perps intelligence: TA, funding, OI, liquidations. Pay-per-call via x402. | clean | — | — | 24.0 |
| 3326 | io.github.0xthaner/reputa Reputa: wallet risk & security plus DeFi cover (insurance) analyses, paid via x402. | clean | — | — | 24.0 |
| 3327 | HackMyIP — no-key IP intelligence Free no-key IP intelligence: geolocation, VPN detection, DNS, WHOIS, blacklists, breach checks | clean | — | — | 24.0 |
| 3328 | freellmpool OpenAI-compatible MCP gateway cataloging 22 LLM providers, with routing, failover, and tools. | clean | — | — | 24.0 |
| 3329 | io.github.1111111111111111111114oLvT2/inquisitor Hypothesis-driven problem solving for AI agents: probe, falsify, escalate. | clean | — | — | 24.0 |
| 3330 | 11agents Cloud MCP Cloud MCP for project data, analytics, research, content planning, media generation, and growth. | clean | — | — | 24.0 |
| 3331 | io.github.15998194110/delta-witness Paid Capture and Guard tools for public-source observations before autonomous actions. | clean | — | — | 24.0 |
| 3332 | ModWrench One MCP server for mod platforms and local modding diagnostics. No data kept. | clean | — | — | 24.0 |
| 3333 | io.github.18boys/matchcv ATS resume checking, job description analysis, and AI resume tailoring powered by MatchCV. | clean | — | — | 24.0 |
| 3334 | Sentieri e condizioni di montagna Italian trails, huts, avalanche bulletins and elevation weather | clean | — | — | 24.0 |
| 3335 | 1Claw Vault HSM-backed vault secrets for AI agents (JIT fetch) plus prompt-injection and threat scanning. | clean | — | — | 24.0 |
| 3336 | 1ClickReport 75 tools for marketing analytics, campaign management and AI monitoring across 7 platforms. | clean | — | — | 24.0 |
| 3337 | io.github.1gr14/agents-party One encrypted channel where Claude Code, Cursor, Codex and any other agent talk to each other. | clean | — | — | 24.0 |
| 3338 | My Painting Club — Painting Lessons Search transcribed painting lessons. Results cite the exact lesson and Vimeo timestamp. | clean | — | — | 24.0 |
| 3339 | io.github.1picassoai/sticky Persistent memory and context for your agent, on a board you can see. Capped, so it stays small. | clean | — | — | 24.0 |
| 3340 | GANO Connector Private GANO MCP for feasibility, scenario analysis, persistence and executive operations. | clean | — | — | 24.0 |
| 3341 | io.github.1shizaan/debugai-mcp MCP server for DebugAI. Browser sign-in, auto client setup, no key pasting. | clean | — | — | 24.0 |
| 3342 | Small Business Intelligence by Brick & Mortar Free joined public records for small business and CRE: Twin Cities parcels, sales, licences | clean | — | — | 24.0 |
| 3343 | Chalkieboard iCloud Read Chalkieboard (iPad) iCloud lesson folders, add materials, append lesson plans. No network. | clean | — | — | 24.0 |
| 3344 | Silk Message other people's AI agents with consent: end-to-end encrypted, on a public ledger. | clean | — | — | 24.0 |
| 3345 | Sense2 Promotional Products 21 tools: search 4,000+ Australian promotional products with live pricing, quotes and curated edits. | clean | — | — | 24.0 |
| 3346 | io.github.26048608982lp-ai/gamenumerics Game numerical design & balance auditing MCP server — 17 deterministic tools, zero LLM guessing. | clean | — | — | 24.0 |
| 3347 | io.github.263311487-ux/dsh-verify Agent-built web app quality gate. Real browser is the judge. PASS/FAIL with receipts. | clean | — | — | 24.0 |
| 3348 | Imprint PDF AI-native print-grade PDF generator. Markdown in, publisher-quality PDF out. | clean | — | — | 24.0 |
| 3349 | io.github.26zl/cybersec-toolkit Authorization-gated MCP server to discover and run 670+ security tools for CTF, pentest, and DFIR. | clean | — | — | 24.0 |
| 3350 | SketchUp MCP Let AI assistants work in SketchUp: quantity takeoff, modeling, materials, screenshots, Ruby. | 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.