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.
59,385
servers indexed
85
with verified activity
20.0
median score
21,857
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 |
|---|---|---|---|---|---|
| 51451 | io.github.infoinlet-marketplace/mcp-notion Notion for AI agents — search, read pages/blocks, query databases, create pages. | clean | — | -0.5 | 10.4 |
| 51452 | io.github.infoinlet-marketplace/mcp-observability Observability for incident agents — query Loki (LogQL), Prometheus (PromQL), Elasticsearch. | clean | — | -0.5 | 10.4 |
| 51453 | io.github.infoinlet-marketplace/mcp-openapi Turn any OpenAPI/Swagger spec into MCP tools — each operation an SSRF-guarded tool. | clean | — | -0.5 | 10.4 |
| 51454 | io.github.infoinlet-marketplace/mcp-postgres-nl-query RLS/tenant-aware Postgres for AI agents — schema, read-only SQL, NL→SQL with safety rails. | clean | — | -0.5 | 10.4 |
| 51455 | io.github.infoinlet-marketplace/mcp-qdrant Read-only Qdrant vector DB for AI agents — collections, info, browse points, count, search. | clean | — | -0.5 | 10.4 |
| 51456 | io.github.infoinlet-marketplace/mcp-redis Read-only Redis for AI agents — keys, hashes, lists, sets, sorted sets, streams, INFO. | clean | — | -0.5 | 10.4 |
| 51457 | io.github.infoinlet-marketplace/mcp-social Multi-platform social posting for AI agents (Postiz) — channels, schedule/publish posts. | clean | — | -0.5 | 10.4 |
| 51458 | io.github.infoinlet-marketplace/mcp-time Time & date for AI agents — timezones, conversion, date math, diffs, cron, business days. | clean | — | -0.5 | 10.4 |
| 51459 | io.github.infoinlet-marketplace/mcp-translate Translation for AI agents — translate, detect, batch; Japanese keigo registers. OpenRouter. | clean | — | -0.5 | 10.4 |
| 51460 | io.github.infoinlet-marketplace/mcp-workflow Workflow automation for AI agents — browse 125 connectors + 234 templates, run via FluxTurn. | clean | — | -0.5 | 10.4 |
| 51461 | Eval Engine API Pay-per-call AI evaluation MCP server. Score LLM outputs against benchmark rubrics via Workers AI. | medium | — | -0.6 | 10.4 |
| 51462 | FableMaker AI story generator — create illustrated storybooks, AI songs, and short AI video films | medium | — | -0.6 | 10.4 |
| 51463 | io.github.jeresalmisto/calcfi-mcp 24 free personal-finance + macro tools (mortgage, paycheck, tax, FRED, BLS) for LLM agents. | clean | — | -0.6 | 10.4 |
| 51464 | io.github.jobrayan/codmir AI-powered task execution, tickets, sprints, error debugging, and desktop control. | clean | — | -0.6 | 10.4 |
| 51465 | Kenva Personal CRM for Claude. Contacts live as plain-text files in your own Google Drive. | medium | — | -0.6 | 10.4 |
| 51466 | ATEX AI Gateway One API key for 6 AI models. Pay-per-use. MCP protocol support with web search. | clean | — | -0.6 | 10.4 |
| 51467 | io.github.lo-nau/localgym-mcp-server Read-only MCP server for UK gym search using the LocalGym Agent API. | clean | — | -0.6 | 10.4 |
| 51468 | io.github.mumega848/mcpwp MCP for WordPress — connect Claude, Cursor, or Windsurf to any WordPress site. | clean | — | -0.6 | 10.4 |
| 51469 | io.github.pixelx-jp/plateau-creative-mcp PLATEAU 3D city data as scene-editing and glTF export tools for creative LLM agents. | clean | — | -0.5 | 10.4 |
| 51470 | Autonoma Agent Services Paid agent trust checks, receipt verification, research, data work, and monitoring. | medium | — | -0.6 | 10.4 |
| 51471 | ACLM Lab Interpreter Interpret lab values against ACLM-optimized ranges. Returns deprescription signals. | clean | — | -0.6 | 10.4 |
| 51472 | Drug-Food Interactions Food-drug interaction and nutrient depletion checks for 30+ common medications. | clean | — | -0.6 | 10.4 |
| 51473 | GLP Companion Nutrition GLP-1 phase-aware nutrition: muscle preservation, GI tolerance, taper protocols. | clean | — | -0.6 | 10.4 |
| 51474 | Lifestyle Medicine Knowledge Semantic search over a 200-chunk ACLM lifestyle medicine knowledge base. | clean | — | -0.6 | 10.4 |
| 51475 | Plant-Based Nutrition Protocols Evidence-based plant-based food-as-medicine protocols for 47 chronic conditions. ACLM-aligned. | clean | — | -0.6 | 10.4 |
| 51476 | io.github.retep-tru/maeil Invite someone to a calendar event by phone number and get their real email back when they accept. | medium | — | -0.6 | 10.4 |
| 51477 | io.github.rohithraju-ops/mcp-ml-lab Run end-to-end ML experiments from natural language (XGBoost, LightGBM, Optuna). | clean | — | -0.6 | 10.4 |
| 51478 | Proton Mail (unofficial) Unofficial Proton Mail MCP — send, read, search & organize email over SMTP and IMAP | clean | — | -0.6 | 10.4 |
| 51479 | io.github.shdomi8599/vibie-mcp Deploy HTML folders to vibie.page from Claude / Cursor — one-line install, OAuth, auto-update. | clean | — | -0.6 | 10.4 |
| 51480 | io.github.tonyback0101-cmyk/buyer-intelligence Find verified global B2B buyers by category & country. Free anonymous discovery. SGX-listed. | clean | — | -0.6 | 10.4 |
| 51481 | LLM CLI Gateway One MCP endpoint for Claude Code, Codex, Gemini, Grok and Mistral CLIs, with durable async jobs. | clean | — | -0.6 | 10.4 |
| 51482 | io.github.viridis-security/injection-detector Formally-verified injection/exfiltration detector for AI agents (MCP-02). | clean | — | -0.6 | 10.4 |
| 51483 | IP Defender Trademark Monitoring MCP Trademark filing monitor across 40+ countries - detect filings that resemble your brand. | medium | — | -0.5 | 10.4 |
| 51484 | api-changelog SDK breaking-change tracker for AI agents — Anthropic/OpenAI/LangChain/MCP/Mistral. | clean | — | -0.6 | 10.4 |
| 51485 | bounty-mcp Live coding-bounty deal-flow from verified-escrow GitHub bounties for AI agents. | clean | — | -0.6 | 10.4 |
| 51486 | cve-cache Recent CVE + GHSA cache for AI agents auditing dependencies (npm/PyPI/Cargo/Maven/Go). | clean | — | -0.6 | 10.4 |
| 51487 | dns-cache DNS/WHOIS/SSL/geo-IP cache MCP server for AI agents. | clean | — | -0.6 | 10.4 |
| 51488 | license-checker OSS license metadata + compatibility checker MCP server. | clean | — | -0.6 | 10.4 |
| 51489 | llm-oracle Up-to-date LLM pricing + availability catalog with cited sources for AI agent routing. | clean | — | -0.6 | 10.4 |
| 51490 | package-meta npm/PyPI/Cargo package metadata + downloads + maintainer health. | clean | — | -0.6 | 10.4 |
| 51491 | regulatory-deadline FinCEN/SEC/EU AI Act/GDPR deadline tracker for AI agents. | clean | — | -0.6 | 10.4 |
| 51492 | status-aggregator Cross-vendor SaaS status aggregator for AI agents (Anthropic/OpenAI/AWS/GH/Stripe/CF). | clean | — | -0.6 | 10.4 |
| 51493 | IA-Asso.fr — French Associations Registry Search 1.26M+ active French associations (official RNA registry, 10 tools, premium & RUP filters) | clean | — | -0.5 | 10.4 |
| 51494 | gitea-mcp Model Context Protocol server for Gitea (and Forgejo, Codeberg). | clean | — | -0.6 | 10.4 |
| 51495 | Healthparse Healthcare Data Gateway Pay-per-call US healthcare data: hospital financials, prices, quality, exclusions, wages. | medium | — | -0.5 | 10.4 |
| 51496 | I Hate Invoicing Send invoices from Claude and ChatGPT. One sentence becomes a PDF with a Stripe payment link. | medium | — | -0.6 | 10.4 |
| 51497 | Whatic IC Datasheets IC datasheet search: parametric part finding, spec lookup, price comparison — grounded in real PDFs. | medium | — | -0.6 | 10.4 |
| 51498 | kz.tehprof.booking/reservations Remote MCP for TehProf Booking: browse resources & availability, create & cancel reservations. | medium | — | -0.5 | 10.4 |
| 51499 | lat.oktopus/checkout-cod Riel de pago contra entrega (COD) para LATAM: crea órdenes y cobra con Dropi vía MCP. | clean | — | -0.6 | 10.4 |
| 51500 | lv.vairogs/vairogs Latvian law search: in-force statutes, verbatim articles, verified Q&A. Anonymous, read-only. | medium | — | -0.6 | 10.4 |
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.