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 |
|---|---|---|---|---|---|
| 48101 | ai.matih/mcp The grounded data layer for any LLM: governed SQL, metrics, lineage and catalog over your data. | clean | — | -0.6 | 13.5 |
| 48102 | at.memebo/memeboat-mcp Search 25,000+ meme templates and create shareable memes on memebo.at. Free, anonymous, no API key. | clean | — | -0.6 | 13.5 |
| 48103 | com.candidcost/mcp Cited, receipt-backed US home-buying data & calculators — education-only, every number sourced. | clean | — | -0.6 | 13.5 |
| 48104 | com.contextser.mcp/nodecel Vibe deployment for nodecel — deploy, roll back, diagnose, and manage apps and domains from chat. | clean | — | -0.5 | 13.5 |
| 48105 | SettlementWitness Remote-first MCP adapter for emitting Settlement Attestation Receipts; not a verifier. | clean | — | -0.5 | 13.5 |
| 48106 | TownBrief - Massachusetts Local Government Intelligence MA local gov meetings, transcripts, articles, bylaws, calendars for 351 towns. | clean | — | -0.6 | 13.5 |
| 48107 | dev.dungbeetle/mcp Visual regression & snapshot testing for AI agents — list runs, read semantic diffs, review. | clean | — | -0.5 | 13.5 |
| 48108 | InfraNode Keyless open data for 84 German cities: 12 lean read-only MCP tools covering 67 data types. | clean | — | -0.6 | 13.5 |
| 48109 | Doriku Shared control plane for AI coding agents — tasks, memory, decisions, file locks. 12 tools. | clean | — | -0.6 | 13.5 |
| 48110 | Grounded Reasoning Verify multi-hop relational claims before an agent asserts them — zero tokens, with proof paths. | clean | — | -0.6 | 13.5 |
| 48111 | GEO Inspector Inspect a site's AI-search readiness: AI crawler access, llms.txt, schema markup, meta directives | clean | — | -0.6 | 13.5 |
| 48112 | io.github.BlackhatShiftey/seam-runtime SEAM: local-first memory runtime for AI agents, with retrieval and glassbox provenance over MCP. | clean | — | -0.6 | 13.5 |
| 48113 | PackageGuard x402-gated safety checker for npm/PyPI packages before you npm install / pip install. | clean | — | -0.6 | 13.5 |
| 48114 | mcp-crewd-rs Cell fabric daemon: spawn and coordinate Claude/Codex/pi worker cells over MCP. Audited. | clean | — | -0.6 | 13.5 |
| 48115 | io.github.DrBaher/supstack Evidence-based supplement research, dosing, safety, and interactions as agent-callable tools. | clean | — | -0.6 | 13.5 |
| 48116 | io.github.Franksterino/citeguard Verify citations in AI text: fetches each cited source, returns verdicts with evidence quotes. | clean | — | -0.6 | 13.5 |
| 48117 | LLM Pulse AI visibility analytics for brand mentions, citations, sentiment, and GEO reports | clean | — | -0.6 | 13.5 |
| 48118 | Compass Ground your LLM in EU financial, crypto and AI regulation, verbatim and cited, via Compass. | clean | — | -0.6 | 13.5 |
| 48119 | io.github.LogicTreeInc/data247 Phone carrier lookup, append, verification, DNC, and fraud data services. | clean | — | -0.6 | 13.5 |
| 48120 | io.github.MetaLift-AI/metalift Metalift MCP for AI agents: web search (2 credits), scrape, crawl, and map tools | clean | — | -0.6 | 13.5 |
| 48121 | io.github.Neji402/engedi 93 tools: finance, weather, news, travel, knowledge, SEO. 27 free + 66 paid via USDC x402. | clean | — | -0.6 | 13.5 |
| 48122 | TradeTi.me — Market Hours Read-only trading hours for 30 stock exchanges — open now, next open, holidays, sessions. | clean | — | -0.6 | 13.5 |
| 48123 | projectmind Persistent project memory for AI coding agents: one compact digest instead of re-reading the repo. | clean | — | -0.6 | 13.5 |
| 48124 | io.github.QoreNext-IT/qorenext-mcp Company hierarchy analysis and address verification via MCP | clean | — | -0.6 | 13.5 |
| 48125 | io.github.SEODesignLab/seo-tools SEO tools via x402: briefs, keywords, SERP, backlinks, audits. $0.50-$3/req USDC on Base. | clean | — | -0.6 | 13.5 |
| 48126 | io.github.Vishisht16/humane-proxy AI safety middleware — detects self-harm and criminal intent in LLM prompts. | clean | — | -0.6 | 13.5 |
| 48127 | io.github.YonasValentin/mcp-memory-graph Local-first memory for Claude Code and any MCP client: hybrid search + knowledge graph, $0/token. | clean | — | -0.6 | 13.5 |
| 48128 | AgentBodega MCP Discover AgentBodega paid data tools, contracts, and x402/L402 HTTP payment handoff metadata. | clean | — | -0.6 | 13.5 |
| 48129 | io.github.apeirontrade/provenance-mcp Wash-traffic risk checks for Algorand x402 endpoints before your agent trusts or pays them. | clean | — | -0.5 | 13.5 |
| 48130 | io.github.apexapi/apexapi-mcp Call 120+ AI models and live web context (scrape/crawl/extract) from any MCP client with one key | clean | — | -0.6 | 13.5 |
| 48131 | io.github.burakaydinofficial/searxng-deepdive MCP server for SearXNG with engine targeting, multi-page fanout, and HTML→Markdown URL reading. | clean | — | -0.6 | 13.5 |
| 48132 | io.github.caglarbozkurt/heimdall Scan an MCP server or agent config for injection, exfiltration, and risky capabilities. | clean | — | -0.5 | 13.5 |
| 48133 | io.github.devzspy/discourse-mcp-extended Discourse MCP server (stdio) with review-queue tools added. Fork of @discourse/mcp. | clean | — | -0.6 | 13.5 |
| 48134 | ValidateFin Validate SEPA, UBL/Peppol, XRechnung, camt, ACH & IBAN files locally — no data leaves your machine. | clean | — | -0.6 | 13.5 |
| 48135 | io.github.elyngved/failmodes MCP server for the Fail Modes taxonomy — a knowledge base of AI system failure modes | clean | — | -0.5 | 13.5 |
| 48136 | Alchemy Serves the Alchemy writing ruleset to any agent, so its prose loses the usual LLM tells. | clean | — | -0.5 | 13.5 |
| 48137 | io.github.forum-labs/payfetch x402 paying-fetch client for AI agents. Spending caps, approval, receipts. Non-custodial. | clean | — | -0.6 | 13.5 |
| 48138 | GST Cranes Public Discovery MCP Public read-only discovery tools for GST Cranes marketplace, wanted ads, and Crane Wiki. | clean | — | -0.6 | 13.5 |
| 48139 | io.github.godesigntech/freelancer-mcp-server Search, bid, and message clients on Freelancer.com from Claude. Multi-account support. | clean | — | -0.6 | 13.5 |
| 48140 | io.github.habedi/omni-lpr An MCP server for automatic license plate recognition | clean | — | -0.5 | 13.5 |
| 48141 | TaxBrainAI MCP 8 offline Indian income-tax MCP tools: deterministic compute, regimes, citations, notices. | clean | — | -0.6 | 13.5 |
| 48142 | io.github.hyperdrift-io/nextrole A job-search companion: tailor your CV to a role, score fit, fix ATS issues. Also via MCP. | clean | — | -0.6 | 13.5 |
| 48143 | ShipPage Publish HTML or Markdown to a public URL in one call. Zero config, auto-registers on first use. | clean | — | -0.6 | 13.5 |
| 48144 | JKTJJ MCP Server BJJ gym, coach, event, and city data for AI agents. Free base tools, x402-paid premium. | clean | — | -0.6 | 13.5 |
| 48145 | JMT x402 Agent Tools 25 x402 paid API tools for AI agents on Base mainnet. | clean | — | -0.6 | 13.5 |
| 48146 | Ignition MCP MCP server for Inductive Automation Ignition: tags, alarms, history, and Perspective | clean | — | -0.6 | 13.5 |
| 48147 | io.github.kozmos-tech/contactapi An open-source API for collecting and managing contacts and signups. | clean | — | -0.6 | 13.5 |
| 48148 | io.github.kozmos-tech/inhalt An open-source headless CMS for managing content models and entries. | clean | — | -0.6 | 13.5 |
| 48149 | io.github.kozmos-tech/yourtraffic Open-source, privacy-first web analytics for tracking your sites' traffic. | clean | — | -0.6 | 13.5 |
| 48150 | io.github.mahmoudilyan/marmo-ui Live React design-system APIs, patterns, and code validation so AI agents build real UI, not slop. | clean | — | -0.6 | 13.5 |
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.