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 |
|---|---|---|---|---|---|
| 34201 | kad.dev Deploy and run web apps from your agent: live URL, Postgres, S3 storage, a version per commit. | medium | — | — | 20.0 |
| 34202 | Canonsheet Consistent prompts for one human character across image and video models. Paid per call, x402. | medium | — | — | 20.0 |
| 34203 | Depcheck Known vulnerabilities for exact package versions from OSV, with fixes. Paid per call, x402. | medium | — | — | 20.0 |
| 34204 | Imagemeta Write SEO metadata (title, alt text, keywords, copyright) into JPEG, PNG, WebP. Paid per call, x402. | medium | — | — | 20.0 |
| 34205 | Jobpost Read the job posting from any career page: title, employer, dates, salary. Paid per call, x402. | medium | — | — | 20.0 |
| 34206 | Kimage Generate original images from text; prompts and results are content-checked. Paid per image, x402. | medium | — | — | 20.0 |
| 34207 | Pagemd Read any public web page as clean Markdown for LLMs, with its metadata. Paid per call, x402. | medium | — | — | 20.0 |
| 34208 | Speak Text to natural speech as MP3: 38 voices, 7 languages, 1,000 chars per call. Paid per call, x402. | medium | — | — | 20.0 |
| 34209 | Keyframer 150+ React Native animation recipes, scene authoring, phone preview via QR, Reanimated v4 codegen | medium | — | — | 20.0 |
| 34210 | Agent Verification Utility Deterministic JSON checks with signed evidence and x402-paid execution | medium | — | — | 20.0 |
| 34211 | KitRank use cases Read-only catalog of 1,900+ real, sourced AI agent use cases with tools, cost and setup prompts. | medium | — | — | 20.0 |
| 34212 | knowsme One memory for you and your AI agents, shared by ChatGPT, Claude, Gemini, Grok, Codex and Cursor. | medium | — | — | 20.0 |
| 34213 | Kognite Hosted agent memory: store, search, and recall facts across sessions from any MCP client. | medium | — | — | 20.0 |
| 34214 | Kuuhaku Ask who calls a route, what a change breaks or who reads a field, across a system's repos. | medium | — | — | 20.0 |
| 34215 | lastseen score Trust scores and dated liveness/drift facts for MCP servers, from the lastseen.dev notary register. | medium | — | — | 20.0 |
| 34216 | Laterbase A shared backlog for the out-of-scope work your coding agents find. | medium | — | — | 20.0 |
| 34217 | Launchdog Launch your product on Launchdog's weekly board from your coding agent: list, verify, badge, book. | medium | — | — | 20.0 |
| 34218 | Launchdog (read-only) Read-only Launchdog board: search this week's launches, past winners and upcoming launch weeks. | medium | — | — | 20.0 |
| 34219 | LaunchFlag Feature flags and kill switches. Turn a shipped feature off in production without a deploy. | medium | — | — | 20.0 |
| 34220 | Layoutline Compose a landing page from layouts observed on real pages, then review the built page for drift. | medium | — | — | 20.0 |
| 34221 | dev.lekta/lekta Audits how AI answer engines read a page and grades it A+ to F across four measured layers. | medium | — | — | 20.0 |
| 34222 | Lettera Messaging and inboxes for AI agents: register, send signed messages, check your inbox, find agents. | medium | — | — | 20.0 |
| 34223 | letterport Real email inboxes for AI agents: create addresses, read mail as JSON, reply in threads. | medium | — | — | 20.0 |
| 34224 | dev.llms-txt-validator/llms-txt-validator Validate a site's llms.txt against the spec: fetches every linked URL, scores it 0-100. | medium | — | — | 20.0 |
| 34225 | Official Logo.dev MCP Find brands, logos and brandmarks, and manage brand subscriptions and webhooks with Logo.dev. | medium | — | — | 20.0 |
| 34226 | ludoteca.dev Open video game database: where to buy each game, store IDs, studios and publishers. | medium | — | — | 20.0 |
| 34227 | theRoom Luiz Cordeiro's room in Curitiba: an AI engineer's portfolio, with a dog and a locked door. | medium | — | — | 20.0 |
| 34228 | Mascotline One mascot, locked once, drawn in any scene on demand and checked against its own identity. | medium | — | — | 20.0 |
| 34229 | Mash Prime Read Mash Prime's essays and build notes on agentic systems, memory, approvals, and workflows. | medium | — | — | 20.0 |
| 34230 | MCPComp Diagnostics Grade an MCP server's auth against the spec and diagnose which layer a failure is in. | medium | — | — | 20.0 |
| 34231 | mcpnav directory Search a directory of MCP servers and get connect configs. Data is CC0/MIT-licensed. | medium | — | — | 20.0 |
| 34232 | Memmo Team memory for AI coding agents and code reviews, reviewed by humans and served over MCP. | medium | — | — | 20.0 |
| 34233 | Mentio Social listening for agents: brand mentions across 16 platforms, scored for relevance and intent | medium | — | — | 20.0 |
| 34234 | MESSORA Scrape, crawl and search the web for AI agents via MCP. | medium | — | — | 20.0 |
| 34235 | dev.metarun/metarun Run App Store Connect from your IDE: pricing, listings, screenshots, releases, AI visibility. | medium | — | — | 20.0 |
| 34236 | Minima Search, write, check, export and share the patches, skills and files in your Minima library. | medium | — | — | 20.0 |
| 34237 | Modem Search customer feedback, topics, people and companies in Modem, and run the Modem Agent. | medium | — | — | 20.0 |
| 34238 | Moltbound Consent and checkout rail for AI agents: 20 US services, passkey approval. Sandbox: simulated data. | medium | — | — | 20.0 |
| 34239 | Monito Test a web app in a real browser from plain English. Passed, failed or cannot verify, with evidence. | medium | — | — | 20.0 |
| 34240 | Patchwire Hourly security advisories for JS, AI and web3 packages: ranges, fixes and exploit conditions. | medium | — | — | 20.0 |
| 34241 | Monton Shared docs for people and their agents: markdown docs and HTML pages with comments and history. | medium | — | — | 20.0 |
| 34242 | SkillTriage Scan AI agent skills, MCP server packages and MCP configs before you install them. Static analysis. | medium | — | — | 20.0 |
| 34243 | Moradas — Portuguese addresses & postal codes Portuguese address autocomplete, postal codes, list checks; typo-tolerant, municipality-first; free. | medium | — | — | 20.0 |
| 34244 | MyMemory Long-term memory for AI assistants: search, read and save your notes, links and documents. | medium | — | — | 20.0 |
| 34245 | My wine Find wines and compare live merchant prices in your region. Fair-deal search, My wine OAuth login. | medium | — | — | 20.0 |
| 34246 | NameFlow Find available domain names with real prices, buy within your limits, and set up DNS. | medium | — | — | 20.0 |
| 34247 | Nanotoll MCP Compress prose for LLM context windows. Per-call USDC billing, signed receipt. | medium | — | — | 20.0 |
| 34248 | Netik Netik services (websites, systems, AI agents) with final prices, priced exactly as the site does. | medium | — | — | 20.0 |
| 34249 | NewTV Twitch for agents: go live with your work, watch other agents live, learn from their playbooks. | medium | — | — | 20.0 |
| 34250 | AgentBridge — Discover A2A Services from MCP Free repository documentation for MCP and A2A agents. Bounded no-signup trial with shared cache. | medium | — | — | 20.0 |
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.