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 |
|---|---|---|---|---|---|
| 4151 | KaiBoard MCP Let AI agents draw on your local-first KaiBoard whiteboards (relay or local folder). | clean | — | — | 24.0 |
| 4152 | GTFS Scorecard Read-only GTFS transit feed scorecards: grades, plain-language fixes, and history. | clean | — | — | 24.0 |
| 4153 | Multidim Structured thinking grids for AI agents: deterministic analysis frames, validation, learned traps | clean | — | — | 24.0 |
| 4154 | Phases Agents Deterministic skill selection: local discovery, strict validation, every skill classified. | clean | — | — | 24.0 |
| 4155 | Local GPU Imagegen MCP-first control plane for ComfyUI workflows with explicit approvals and no silent downloads. | clean | — | — | 24.0 |
| 4156 | io.github.ChiR24/unreal-engine-mcp Automate the Unreal Editor (UE 5.0-5.8): levels, Blueprints, UI, materials, VFX and more. | clean | — | — | 24.0 |
| 4157 | io.github.Chidi09/variantrade Read your VarianTrade portfolio, positions, risk and signals. Trades are proposal-only. | clean | — | — | 24.0 |
| 4158 | io.github.ChloePark85/picright License-aware images for markdown: CC/stock search, screenshots, Mermaid diagrams, provenance | clean | — | — | 24.0 |
| 4159 | SendGrid Secure Security-first SendGrid MCP server: dry-run default, recipient allowlists, rate caps, audit log. | clean | — | — | 24.0 |
| 4160 | Optical Context MCP Compress OCR-heavy PDFs into dense packed images so agents can work with long visual documents. | clean | — | — | 24.0 |
| 4161 | io.github.Chris221/ftp-ssh-mcp Work with a remote host over FTP/FTPS/SFTP, SSH, and MySQL. | clean | — | — | 24.0 |
| 4162 | io.github.Christebob/meta-stamp-pockets Attribution and settlement infrastructure for AI agent content access over HTTP 402 and MCP. | clean | — | — | 24.0 |
| 4163 | Technical Answer Validator Rubric-based technical answer feedback for AI agents; human review required. | clean | — | — | 24.0 |
| 4164 | io.github.Christopher-AS/riv-mcp Riv MCP: spend authorization and governed trading (place_order, positions, market data, policies). | clean | — | — | 24.0 |
| 4165 | Chrome DevTools MCP MCP server for Chrome DevTools | clean | — | — | 24.0 |
| 4166 | Kiwoom Securities MCP Server Read-only MCP server for the Kiwoom Securities REST API: market data, account inquiry, ISA tax tool | clean | — | — | 24.0 |
| 4167 | io.github.Churman1113/pingcheck-mcp PingCheck status monitoring for AI agents. Read public pages or your own monitors via pk_ API key. | clean | — | — | 24.0 |
| 4168 | io.github.Cifero74/mcp-apple-music Apple Music MCP server — search catalog, manage playlists, and access your library via Claude. | clean | — | — | 24.0 |
| 4169 | open-signals Public hazard, water, weather and EPA data with source, age and licence on every reading. | clean | — | — | 24.0 |
| 4170 | io.github.ClawCall-Dev/clawcall Real US phone calls for AI agents: navigates phone menus, waits on hold, returns transcripts. | clean | — | — | 24.0 |
| 4171 | ClickHouse Official ClickHouse MCP server for querying and exploring ClickHouse clusters and chDB. | clean | — | — | 24.0 |
| 4172 | Clipform Interactive video forms that capture authentic responses. Build engaging forms in minutes. | clean | — | — | 24.0 |
| 4173 | io.github.ClockNext/mcp Meter usage and manage usage-based billing from AI tools via the ClockNext API. | clean | — | — | 24.0 |
| 4174 | io.github.Clocknext/mcp Meter usage and manage usage-based billing from AI tools via the ClockNext API. | clean | — | — | 24.0 |
| 4175 | CPersona Persistent AI memory in one SQLite file: 3-layer hybrid search, confidence scoring, 29 tools. | clean | — | — | 24.0 |
| 4176 | io.github.Clousd-Android/clousd-mcp A real Android phone in the cloud for MCP agents: observe the screen, act, reset to a saved state. | clean | — | — | 24.0 |
| 4177 | SAP ABAP MCP Develop, test, analyze, and operate SAP ABAP systems through ADT from AI coding agents. | clean | — | — | 24.0 |
| 4178 | io.github.CodeAlive-AI/codealive-mcp Semantic code search and analysis from CodeAlive for AI assistants and agents. | clean | — | — | 24.0 |
| 4179 | io.github.CodeLogicIncEngineering/codelogic-mcp-server An MCP Server to utilize Codelogic's rich software dependency data in your AI programming assistant. | clean | — | — | 24.0 |
| 4180 | DDMarketer Find and validate SaaS ideas from real user complaints, scored for commercial intent. | clean | — | — | 24.0 |
| 4181 | Wever Labs Agent Products Agent commerce: 27 tools, 10 production services, signed authority, planning, Base USDC x402. | clean | — | — | 24.0 |
| 4182 | TaskMarket Discover funded agent work and prepare approval-gated TaskMarket delegations. | clean | — | — | 24.0 |
| 4183 | io.github.CodesWhat/portkey-admin-mcp Portkey Admin API control-plane MCP server with Prisma AIRS interoperability guidance. | clean | — | — | 24.0 |
| 4184 | Unity API Documentation Accurate Unity API docs (2022/2023/6) for AI agents. Prevents hallucinated signatures. | clean | — | — | 24.0 |
| 4185 | Unreal Engine API Documentation Accurate UE5 C++ API docs for AI agents. Prevents hallucinated signatures and includes. | clean | — | — | 24.0 |
| 4186 | The Remote Suite Appreciate teammates, celebrate milestones, and run workspace ops from MCP clients via OAuth. | clean | — | — | 24.0 |
| 4187 | The Remote Suite (Dev) Dev environment for The Remote Suite MCP. Appreciate teammates and run workspace ops. | clean | — | — | 24.0 |
| 4188 | Agent Coherence — Stale Write Guard (FS) Coherence guard for shared files: denies stale writes so agents don't silently overwrite each other. | clean | — | — | 24.0 |
| 4189 | CoinRithm Agent Trading Keyless prediction-market data across 12 venues plus paper-trading of crypto spot, futures, and PM. | clean | — | — | 24.0 |
| 4190 | io.github.Coinlooter/mcp PayFlowAgent suite: token intel, DeFi, enrich, Base trust (x402). | clean | — | — | 24.0 |
| 4191 | Synaptic Code Intelligence Code intelligence for repository graphs, change impact, test selection, and engineering memory. | clean | — | — | 24.0 |
| 4192 | io.github.CommonNinja/commonninja-mcp-server Create, update, and manage live Common Ninja website widgets in natural language. 100+ widget types. | clean | — | — | 24.0 |
| 4193 | ComplyEaze Bridge Reads TallyPrime for your AI assistant; posts only vouchers you approve. Windows, Apple Silicon Mac. | clean | — | — | 24.0 |
| 4194 | ComplyEdge TrustLint — offline EU AI Act compliance checks Offline TrustLint checks: EU AI Act Article 5, Article 50, GPAI, plus GDPR and HIPAA. | clean | — | — | 24.0 |
| 4195 | Compabase 3M+ Polish companies (KRS, CEIDG): financials, people, rankings and public registries. | clean | — | +7.8 | 24.0 |
| 4196 | Economic Statistics Official economic statistics for AI agents: GDP, inflation, trade and debt for 150+ countries. | clean | — | — | 24.0 |
| 4197 | Health Statistics Health statistics for AI agents: life expectancy, causes of death, health spending, WHO data. | clean | — | — | 24.0 |
| 4198 | Labour Market Statistics Labour market statistics for AI agents: unemployment, employment and wages for 150+ countries. | clean | — | — | 24.0 |
| 4199 | Monitly Official statistics for AI agents: Eurostat, World Bank, OECD, IMF and WHO data for 150+ countries. | clean | — | — | 24.0 |
| 4200 | Polish Company Financials Polish company financial statements for AI agents: revenue, profit, assets, rankings, benchmarks. | 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.