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.
54,385
servers indexed
86
with verified activity
20.0
median score
19,556
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 |
|---|---|---|---|---|---|
| 45301 | Mixer4AI Mixer4AI — verified AI agents, trusted introductions, for agents acting for real businesses. | medium | — | -0.5 | 11.9 |
| 45302 | OntoRamp Decision Intelligence Log, evaluate, and ground AI decisions against authority context. Returns PASS, WARN, or BLOCK. | clean | — | -0.6 | 11.9 |
| 45303 | OntoRamp Knowledge Cartographer Knowledge coverage map and health score. Ingest docs into a governed knowledge graph via MCP. | clean | — | -0.6 | 11.9 |
| 45304 | com.pirchjobs/pirch Verified job search: every listing confirmed live and accepting applicants within the last 72h. | medium | — | -0.6 | 11.9 |
| 45305 | Ranomics Platform Wet-lab triage for AI binder-design agents. Yeast display, mammalian display, DMS at library scale. | clean | — | -0.6 | 11.9 |
| 45306 | SeoGrep SEO for AI agents: crawl sites, audit pages, pull Search Console data, generate shareable reports. | medium | — | -0.5 | 11.9 |
| 45307 | Suited Tailored, graded job applications: a CV, cover letter and form answers built per vacancy. | medium | — | -0.6 | 11.9 |
| 45308 | com.sulvo.publisher-revenue-audit/audit Publisher revenue audit: ads.txt and ad-stack checks, Sulvo onboarding, and Boost ad-block recovery | medium | — | -8.1 | 11.9 |
| 45309 | Company Intel 9 pay-per-call company intel tools over MCP. Free discovery, calls settle in USDC on Base (x402). | medium | — | -0.6 | 11.9 |
| 45310 | SEO Tools 5 pay-per-call SEO tools over MCP. Free discovery, tool calls settle in USDC on Base via x402. | medium | — | -0.6 | 11.9 |
| 45311 | Web Intel 8 pay-per-call web intel tools over MCP. Free discovery, calls settle in USDC on Base (x402). | medium | — | -0.6 | 11.9 |
| 45312 | Dango Build decks in your own brand, from the AI agent you already use. Then edit them yourself. | medium | — | -0.6 | 11.9 |
| 45313 | com.tunnelpowered/knowledge-base Search verified local businesses, check what their verification proves, and message them. | medium | — | -8.1 | 11.9 |
| 45314 | UseWait Create and manage waitlists from your AI agent: page, custom domain, emails, signups, broadcasts. | medium | — | -0.5 | 11.9 |
| 45315 | Vendo AI Autonomous AI sales: agents, signal-based prospecting, outreach, CRM — 149 tools. | medium | — | -8.1 | 11.9 |
| 45316 | MatFlow Read-only MatFlow data: pricing, competitors, features, FAQs for combat-sports gyms. | clean | — | -0.6 | 11.9 |
| 45317 | com.zeltser/website-search Improve security writing, score it against rubrics, plan IR, CTI, vuln, and product strategy. | clean | — | -0.6 | 11.9 |
| 45318 | Zoxron MCP Your AI agent deploys, migrates & upgrades self-hosted Odoo ERP on a server you own. | medium | — | -0.6 | 11.9 |
| 45319 | Alloy AI workspace — shared knowledge, skills, and tools for AI agents | clean | — | -0.6 | 11.9 |
| 45320 | Website Change Monitor Monitor public pages and JSON endpoints after agents disconnect, with polling and webhooks. | medium | — | -0.6 | 11.9 |
| 45321 | SpatialPack — 3D asset readiness Test whether 3D assets survive Apple Quick Look and Safari <model>, then fix what fails | medium | — | -0.6 | 11.9 |
| 45322 | ClearMarket Reference data for prediction markets: graded resolution clarity, cross-venue links, provenance. | clean | — | -0.5 | 11.9 |
| 45323 | AdTAO MCP Google Ads MCP with 20,000+ account peer context and staged approve-then-execute writes. | medium | — | -8.1 | 11.9 |
| 45324 | Air Pipe Build, validate, deploy — HTTP APIs, cron jobs, webhooks and MCP tools — from your AI client. | medium | — | -8.1 | 11.9 |
| 45325 | FixYourDocs File structured docs-feedback reports to the FixYourDocs hub via a file_doc_feedback tool. | clean | — | -0.6 | 11.9 |
| 45326 | getMe MCP Server An MCP server that exposes getMe key-value operations as MCP tools | clean | — | -0.6 | 11.9 |
| 45327 | AI Firewall MCP Multi-agent LLM security layer detecting prompt injection and jailbreaks. | clean | — | -0.5 | 11.9 |
| 45328 | io.github.BasilSkyWalk/parecode Token-aware ripgrep code search and atomic multi-file edits for coding agents. | clean | — | -0.6 | 11.9 |
| 45329 | io.github.CSOAI-ORG/supply-chain-mcp Supply chain management and logistics tools for AI agents. Capabilities: shipment tracking | clean | — | -0.6 | 11.9 |
| 45330 | io.github.Casterdly/jarvis-market-signals Live crypto market signals for AI agents: perp liquidations, funding, OI positioning, yield, FX. | clean | — | -0.6 | 11.9 |
| 45331 | Closeread Verify A verified dependency-audit verdict any AI agent can call over MCP, not a raw scan. | clean | — | -0.6 | 11.9 |
| 45332 | io.github.Jarroslav/agentic-os Read-only, never-executing MCP server for the agentic-os governance, SDLC, and QE methodology. | medium | — | -8.1 | 11.9 |
| 45333 | io.github.Jott2121/agent-gate Fail-closed quality gate and hash-chained receipt ledger for AI agent workflows. | clean | — | -0.6 | 11.9 |
| 45334 | KrystalView Analytics Read-only MCP access to sessions, funnels, campaigns, errors, live visitors, and anomalies. | clean | — | -0.6 | 11.9 |
| 45335 | Pressbooks Search for books and book-related products, with access to product and delivery details | medium | — | -0.6 | 11.9 |
| 45336 | io.github.Natden444/pickanagency Search 47,000+ marketing agencies and get AI-matched with fitted agencies, from Pick an Agency. | clean | — | -0.6 | 11.9 |
| 45337 | AgentCron Schedule tasks for later from your AI agent: reminders, delayed webhooks, recurring jobs. | clean | — | -0.6 | 11.9 |
| 45338 | AgentPing Let your AI agent notify you by email, Slack, Discord, or webhook. One tool: send_notification. | clean | — | -0.5 | 11.9 |
| 45339 | io.github.RyanByrne/validatethat-mcp Run UX research from Claude — create card sort studies, list studies, pull headline stats. | clean | — | -0.5 | 11.9 |
| 45340 | eyeot ERP ERP français avec serveur MCP natif : plus de 1 800 actions métier auto-générées via OpenAPI. | clean | — | -0.5 | 11.9 |
| 45341 | ChainScope Multi-chain wallet intelligence: balances, transactions, ENS, OFAC screening across 7 chains. | medium | — | -8.1 | 11.9 |
| 45342 | Concordance Cross-source search across 18 real-time data sources, source-cited and corroboration-checked. | medium | — | -8.1 | 11.9 |
| 45343 | Trading Strategy Data Live crypto trend signals, ranking, and backtesting for BTC/ETH/SOL/XRP/ADA. x402 pay-per-call. | medium | — | -8.1 | 11.9 |
| 45344 | TrustFetch Prompt-injection scanning and safe webpage fetching for AI agents reading untrusted content. | medium | — | -8.1 | 11.9 |
| 45345 | CRE Intelligence Live CRE analysis: Federal Reserve rates, Census 1/3/5-mile demographics, DCF models, IC memos. | clean | — | -0.6 | 11.9 |
| 45346 | io.github.aiconsulting06000-tech/acf-mcp Official ACF® MCP server — Agentic Commerce Framework® governance copilot for AI assistants. | clean | — | -0.6 | 11.9 |
| 45347 | io.github.amitsha86/furlen-mcp Turn a CSV or a named public dataset into an animated chart video, figures re-checked first. | medium | — | -0.6 | 11.9 |
| 45348 | llmsmap.me International Directory Read-only search and discovery for the international llms.txt directory maintained by llmsmap.me. | medium | — | -0.6 | 11.9 |
| 45349 | dappgrade — onchain app health index Pre-transaction health and safety verdicts for onchain apps, by contract address. | medium | — | -0.6 | 11.9 |
| 45350 | io.github.azeth-protocol/mcp-server Smart accounts, x402 payments, on-chain reputation, and service discovery for AI agents | clean | — | -0.6 | 11.9 |
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.