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
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 |
|---|---|---|---|---|---|
| 7201 | AI Process Manager (AIPM) Structured Windows state for AI agents: processes, windows, UI trees. No screenshots. | clean | — | — | 24.0 |
| 7202 | io.github.agtrepo/agtrepo-memory Encrypted, pay-per-use persistent memory storage for AI agents, gated by x402 payments on Base. | clean | — | — | 24.0 |
| 7203 | io.github.agustincf/arcade1v1 Play 1v1 arcade games vs AI agents & humans, ranked by ELO, or Aleph: a 4–8 agent table, one pot. | clean | — | — | 24.0 |
| 7204 | Workstream Shared task ledger for AI agents and humans: atomic claims, state machine, GitHub and Slack sync | clean | — | — | 24.0 |
| 7205 | P2Predict Local MCP server for parametric price benchmarking in procurement and engineering. | clean | — | — | 24.0 |
| 7206 | Al Jazeera 360 Browse, search & watch Al Jazeera 360's Arabic shows, documentaries and podcasts inside the chat. | clean | — | — | 24.0 |
| 7207 | Egypt Research Commons Source-grounded research for Egyptian public affairs | clean | — | — | 24.0 |
| 7208 | CoreTend Read-only view of what fills a Mac: disk usage, cleanup candidates, largest items, app leftovers. | clean | — | — | 24.0 |
| 7209 | io.github.ahoybuoy/buoy The design system your coding agents check before they ship: tokens plus exact UI fixes. | clean | — | — | 24.0 |
| 7210 | io.github.ai-hub-open/vk-ads-mcp MCP server for VK Ads API: campaigns, audiences, budgets, stats. Click.ru, token or OAuth. | clean | — | — | 24.0 |
| 7211 | io.github.ai-hub-open/yandex-direct-mcp MCP server for Yandex Direct API: campaigns, ads, keywords, bids, reports. Click.ru or OAuth. | clean | — | — | 24.0 |
| 7212 | AIDISH — AIエージェントから受取注文できる飲食店 Pickup orders at Japanese restaurants for AI agents: find stores, read menus, place orders. No auth. | clean | — | — | 24.0 |
| 7213 | Makefile MCP Expose trusted GNU Make targets as governed MCP tools without a generic shell. | clean | — | — | 24.0 |
| 7214 | text-to-reality Turn an idea into a device anyone can build: parts, printed parts, wiring, code and a picture guide. | clean | — | — | 24.0 |
| 7215 | Sparewise Why is my Windows drive full? Free space safely, within limits you set. Never deletes permanently. | clean | — | — | 24.0 |
| 7216 | AI Ball — AI football match analysis Football match outcome probabilities recorded before kick-off, and an open record of results. | clean | — | — | 24.0 |
| 7217 | io.github.aibenyclaude-coder/kira Skills and Scars for AI agents - your agent records its failures and never repeats them. | clean | — | — | 24.0 |
| 7218 | io.github.aicanvas-me/aicanvas Browse and install 75+ free animated, shadcn-compatible React components from AI Canvas. | clean | — | — | 24.0 |
| 7219 | io.github.aicayzer/companies-house UK Companies House public register: search companies, officers, ownership, filings and documents. | clean | — | — | 24.0 |
| 7220 | Plushwipes Agent Revenue Read-only tools for evaluating a live Plushwipes performance-commission opportunity. | clean | — | — | 24.0 |
| 7221 | Astro Agents - deterministic Western + Vedic astrology Natal charts, transits, kundli, dashas, panchang, Gun Milan. JPL DE440, no LLM, hashed. | clean | — | — | 24.0 |
| 7222 | io.github.aidc2026ai-melon/aidc-mcp-server AIDC MCP for OPR/BOD sizing, validation, and rackPlan layout from the shared 3D graph. | clean | — | — | 24.0 |
| 7223 | io.github.aidemd-mcp/server MCP server that teaches any AI agent the AIDE methodology via progressive disclosure | clean | — | — | 24.0 |
| 7224 | io.github.aidevelopers2/claudeclear-mcp Remove the Claude text watermark by rewriting text, and strip C2PA/EXIF metadata from images. | clean | — | — | 24.0 |
| 7225 | Collar Guardrail — Pre-Trade Risk Layer Deterministic pre-trade risk checks for AI agents on Robinhood Chain. Returns allow/warn/deny. | clean | — | — | 24.0 |
| 7226 | Pagent Hosted MCP for Pagent: review Bayesian A/B tests, capture hypotheses, manage websites via OAuth. | clean | — | — | 24.0 |
| 7227 | botbar — a bar for AI agents A social venue for AI agents: rooms, conversations humans can watch, drinks that teach skills. | clean | — | — | 24.0 |
| 7228 | LLM Configurator Read-only: which local LLMs a GPU or Mac can run - VRAM fit, tokens/sec, model specs. | clean | — | — | 24.0 |
| 7229 | Aileron Journal Read-only queries over Aileron audit journals: verify integrity, search recorded tool calls | clean | — | — | 24.0 |
| 7230 | EDGAR Answers Normalized SEC EDGAR data for AI agents: XBRL financials, 10-K risk diffs, Form 4 insider trades. | clean | — | — | 24.0 |
| 7231 | AIRAS Automated AI research toolkit: hypothesis generation, experiments, and paper writing | clean | — | — | 24.0 |
| 7232 | ShipASO Audit any App Store or Google Play listing: measured ranks, keyword gaps, draft copy. Read-only. | clean | — | — | 24.0 |
| 7233 | BotKelp Verified Next.js component scaffolds via remote HTTP MCP, with integrity stamps for Claude/Cursor. | clean | — | — | 24.0 |
| 7234 | io.github.aistastudio/myc Task queue, decisions and memory for coding agents. Local SQLite, no network. Requires Bun. | medium | — | — | 24.0 |
| 7235 | AIStorageDepot Prompt, rules, skills & docs library over MCP. No token = read-only sample of the public library. | clean | — | — | 24.0 |
| 7236 | veto Turn OpenAPI services into tools an agent can call under your rules. | clean | — | — | 24.0 |
| 7237 | LibKa Write accessible documents: one Markdown file to checked, signed web pages, PDFs, slides, Word. | clean | — | — | 24.0 |
| 7238 | Toolars Local-first dev utilities: hash, base64, JWT, UUID, cron, URL codec. No network or telemetry. | clean | — | — | 24.0 |
| 7239 | io.github.ajanani1/agentreader-mcp 11 pay-per-call web tools for AI agents, auto-paid in USDC on Base via x402. No API keys. | clean | — | — | 24.0 |
| 7240 | io.github.ajeermahmood/bouncer-gates Stops secrets, cross-tenant queries and unsafe migrations before they merge. | clean | — | — | 24.0 |
| 7241 | io.github.ajemba/codasms-mcp Receive one-time SMS/OTP verification codes via the CODASMS API: get a number, wait, release. | clean | — | — | 24.0 |
| 7242 | World Resolver Resolve real-world capability gaps: validate native MCPs, search the web, and record unmet demand. | clean | — | — | 24.0 |
| 7243 | Waqi — AI Privacy Layer Redacts PII from your business tools before the AI sees them — with a provable audit log. | clean | — | — | 24.0 |
| 7244 | Charlotte Area Transit (CATS) CATS bus and light rail trip planning, live arrivals, timetables, routes, and service alerts | clean | — | — | 24.0 |
| 7245 | Charlotte Open City Data Charlotte and Mecklenburg County open data: addresses, crime, 311, zoning, budget, and services | clean | — | — | 24.0 |
| 7246 | CanaryGuard 402 Deterministic prompt-injection detection & sanitization for AI agents via x402 on Base. | clean | — | — | 24.0 |
| 7247 | RugShield 402 Real-time token contract safety scanner and honeypot auditor via x402 on Base. | clean | — | — | 24.0 |
| 7248 | StealthGuard 402 Stealth web extraction, Polymarket alpha, and on-chain pre-trade gating via x402 on Base. | clean | — | — | 24.0 |
| 7249 | x402 Agent Tollbooth On-chain DeFi smart contract auditor, arbitrage scanner, and agent tollbooth via x402 on Base. | clean | — | — | 24.0 |
| 7250 | x402 Sniper Bot Dual-chain autonomous DEX sniper, honeypot protection, and smart-money netflow for Solana & Base. | 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.