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 |
|---|---|---|---|---|---|
| 4351 | Income Factory Toll Fabric Eight metered machine-intelligence tools for AI agents with native x402 payment paths. | clean | — | — | 24.0 |
| 4352 | Lium Docs Search and read the Lium GPU rental docs: pods, CLI, SDK, REST API and agent guides. | clean | — | — | 24.0 |
| 4353 | io.github.Davedat-110105/mcp-gateway Curated gateway to snapshot-versioned Canadian public data services with source provenance. | clean | — | — | 24.0 |
| 4354 | Sitalk Find people with real experience. Bring their approved workflows and decisions into your agent. | clean | — | — | 24.0 |
| 4355 | io.github.DavidFuchs/mcp-uptime-kuma A Model Context Protocol (MCP) server for Uptime Kuma version 2. | clean | — | — | 24.0 |
| 4356 | FlowScope UX Flow Analyser Turn YouTube product demos into structured UX flow reports, and compare demos side by side. | clean | — | — | 24.0 |
| 4357 | Ara — audits d'accessibilité RGAA Piloter des audits RGAA 4.1 sur Ara, référentiel embarqué. Non officiel. | clean | — | — | 24.0 |
| 4358 | io.github.Davmunrey/trazum Trazum as an MCP server: let an agent price and budget its own prompts before it sends them. | clean | — | — | 24.0 |
| 4359 | io.github.Dayananda-D/devcdp Chrome DevTools for AI assistants: console, network, DOM, source maps, breakpoints, live variables. | clean | — | — | 24.0 |
| 4360 | Claw Post Agent social posting via your logged-in Chrome. Remote MCP + OAuth. Not clawpost.dev. | clean | — | — | 24.0 |
| 4361 | XRPLHub — XRPLScore, MPT issuer risk & payment pre-checks XRPL wallet scores, wallet permissions, batch send, MPT risk, screening, pre-checks. Never signs. | clean | — | — | 24.0 |
| 4362 | CarMaker Drive IPG CarMaker for Simulink: run test runs, read results, edit vehicle data and parameters. | clean | — | — | 24.0 |
| 4363 | DealMachine Search and enrich US property, owner, people, and company data for sales and lead generation. | clean | — | — | 24.0 |
| 4364 | io.github.Declade/lucairn-mcp-server Pseudonymizes PII before your LLM and returns a cryptographically signed receipt per response. | clean | — | — | 24.0 |
| 4365 | io.github.Decodo/mcp-server Enable your AI agents to scrape and parse web content dynamically, including geo-restricted sites | clean | — | — | 24.0 |
| 4366 | Deep Agentic Core MCP Unified MCP server for AgenticLens and Agentic Chaos capabilities. | clean | — | — | 24.0 |
| 4367 | Deepsleuth Deterministic, no-LLM security scanner for MCP servers, plus an inline proxy gate. | clean | — | — | 24.0 |
| 4368 | io.github.Deesmo/arch-tools-mcp 63 production tools for AI agents — one API key, pay per call in USDC (x402) or Stripe credits. | clean | — | — | 24.0 |
| 4369 | DLBrowser Self-healing web access for AI agents — recovers through bot blocks, captchas and JS pages. | clean | — | — | 24.0 |
| 4370 | hubmesh Deterministic multi-hop graph retrieval for RAG. Zero LLM calls in the query path. | clean | — | — | 24.0 |
| 4371 | io.github.Dempty-glitch/z-zero-mcp Payments for AI agents: gasless USDC on Base + JIT single-use virtual cards, PAN never in context. | clean | — | — | 24.0 |
| 4372 | Scumble Agents drive a layered AI inpainting editor: select by text, inpaint, mask, layers, PSD/ORA export. | clean | — | — | 24.0 |
| 4373 | Lombardia Trains Live Lombardy train boards, delays, platforms, and journey planning. No API key. | clean | — | — | 24.0 |
| 4374 | io.github.DennisPrediger/slac-mcp MCP server exposing SLAC (Simple Logic & Arithmetic Compiler) as tools for LLM agents | clean | — | — | 24.0 |
| 4375 | io.github.DesMartin01/inferenceindexer-mcp AI inference pricing for agents: live and historical model prices, provider comparison. | clean | — | — | 24.0 |
| 4376 | Desearch AI search, X search, web search, page extraction, and X trends. | clean | — | — | 24.0 |
| 4377 | Codebase Memory Codebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens. | medium | — | — | 24.0 |
| 4378 | GammaRips Options Intelligence Anti-firehose options-flow data for AI agents: curated daily pool, features, realized outcomes. | clean | — | — | 24.0 |
| 4379 | ZeroDOM Deterministic DOM perception for AppSec red teams and AI agents: live Chrome, attack-surface scans. | clean | — | — | 24.0 |
| 4380 | TridentChain Security Local supply-chain CVE scanner via OSV/NVD. Scans deps and IDE extensions. No upload. | clean | — | — | 24.0 |
| 4381 | io.github.Developyn/laver-mcp Kanban boards, sprints, tickets and a team wiki, with versioned writes for concurrent agents. | clean | — | — | 24.0 |
| 4382 | KnowledgeRail Persistent, evidence-backed project knowledge and task context for coding agents. | clean | — | -51.6 | 24.0 |
| 4383 | io.github.DeviceIngineering/ozon-mcp-server Ozon Seller & Performance API, 156 tools; responses trimmed 476k to 64k tokens. | clean | — | — | 24.0 |
| 4384 | io.github.DeviceIngineering/wb-mcp-server Wildberries Seller API, 197 tools; responses measured and trimmed: 770k to 75k tokens. | clean | — | — | 24.0 |
| 4385 | upAPI All public upAPI operations as MCP tools: web scraping, search, screenshots, PDF, OCR and more. | clean | — | — | 24.0 |
| 4386 | npx-vibe Read-only npm package and project dependency preflight tools for AI applications. | clean | — | — | 24.0 |
| 4387 | Windframe Provides style context & tokens to design or restyle web UIs in any framework | clean | — | — | 24.0 |
| 4388 | io.github.Dgotlieb/verdict-mcp Sandboxed test runs for coding agents: compact typed verdicts with failure fingerprints and history | clean | — | — | 24.0 |
| 4389 | io.github.Dhevenddra/forensic-deepdive Persistent code knowledge graph + 9 composite MCP tools for AI coding agents. | clean | — | — | 24.0 |
| 4390 | io.github.Dhi13man/oorep-mcp MCP server and TypeScript SDK for OOREP homeopathic repertory and materia medica reference data. | clean | — | — | 24.0 |
| 4391 | Deadlatch Local advisory pre-trade risk gate for agents. Never places orders. | clean | — | — | 24.0 |
| 4392 | B2B Lead Enrichment Remote MCP server to enrich company profiles with structured B2B data and confidence scores. | clean | — | — | 24.0 |
| 4393 | RPG Maker MV Ultimate MCP RPG Maker MV Ultimate: AI copilot to generate, edit and understand RPG Maker MV projects (MCP) | clean | — | — | 24.0 |
| 4394 | Autonomy Foundry Governance Governance and agentic-commerce policy tools for AI agents: spend, purchase and charter controls. | clean | — | — | 24.0 |
| 4395 | DiffCI Fail-closed, change-aware verification for AI coding agents with affected-test guidance. | clean | — | — | 24.0 |
| 4396 | Colour Memory Colour meaning, history and evidence for AI: 45,000+ source-graded colour records and 91 tools. | clean | — | +11.0 | 24.0 |
| 4397 | io.github.DigiCatalyst-Systems/dep-diff-mcp Translates a lockfile diff into a human-readable upgrade plan for npm, PyPI, and GitHub Actions. | clean | — | — | 24.0 |
| 4398 | io.github.Digilac/simap-mcp MCP server for simap.ch - Swiss public procurement platform | clean | — | — | 24.0 |
| 4399 | io.github.Digital-Threads/token-pilot Save up to 80% tokens when AI reads code via AST-aware structural reading | medium | — | — | 24.0 |
| 4400 | io.github.DigitalCurrensy/aio-geo AIO.GEO: audit, dry-run fixes, rescore, doctor. Remote + stdio. Not LLM rankings. | 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.