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

Leaderboard

Activity & maintenance, not security — how this is scored
MCP servers ranked by activity and maintenance score, highest first.
#ServerFlagsStarsChangeScore
401Rokha
Search a registry of agent skills and MCP servers, then run them for real. No install, traced.
clean——
24.0
402runx
The governed runtime for agent skills. Search the catalog and inspect a skill before running it.
clean——
24.0
403ai.ruthven/ruthven
Read-only artwork provenance: Origin Passports, evidence states, Merkle proofs checkable on Ethereum
clean——
24.0
404ai.safe4/safe4
Tests an AI agent's purchase against the task it was given. Paid per call in USDC via x402.
clean——
24.0
405Salt
Your agent asks humans on Salt and gets answers: messages, tap-to-answer cards, invoices.
clean——
24.0
406Sato Kit
Prepare -> execute for onchain agent actions: policy pre-flight, simulation, receipt log.
clean——
24.0
407Sato Hub: Onchain Agents
Search scored onchain-agent tooling: frameworks, MCP servers, wallets, x402 rails, deploy specs.
clean——
24.0
408ai.saymaker/saymaker-mcp
Generate and edit AI images and video on SayMaker: Veo 3.1, Kling 3.0, Seedance 2.0, Nano Banana 2.
clean——
24.0
409Scrapewise
Scrape, clean and match product and price data from any website
clean——
24.0
410ai.sealgate/gateway
MCP gateway with runtime security policy, tool-call-level control, and audit of agent actions.
clean——
24.0
411SearchConsole.ai
Read-only Search Console analytics, URL inspection, indexing diagnostics, and sitemaps.
clean——
24.0
412Searcher OS
AI agent access to your Searcher OS deal feed, pipeline, buy boxes, CIM analysis, and broker CRM.
clean——
24.0
413Selda
Find customers, research each one and draft the outreach. Nothing sends without approval.
clean——
24.0
414ai.sellermate/amazon-ads
Ask your Amazon Ads account anything and act with guardrails. Remote MCP, OAuth, free to connect.
clean——
24.0
415Sellinger CRM
Manage Sellinger AI SDR CRM leads, conversations and pipeline from any MCP client.
clean——
24.0
416Sendinel
AI-controlled email ops for campaigns, contacts, segments, analytics, and sending.
clean——
24.0
417ai.sendraven/mcp
Email infrastructure for AI agents: send, read replies as threads, campaigns, per-key limits.
clean——
24.0
418ai.sentfrom/mcp
Email for AI agents: inboxes, send/reply/forward, search, threads, webhooks — 21 SentFromAI tools.
clean——
24.0
419SEOmatic
SEO agent: GSC, keyword, backlink and AI-visibility insights, plus approval-gated site actions
clean——
24.0
420ai.shipeasy/mcp
Feature flags, A/B experiments, kill switches, dynamic config & i18n — Shipeasy MCP server.
clean——
24.0
421ai.shippp/mcp
Deterministic Chakra UI code from your Shippp design files, straight into your IDE agent.
clean——
24.0
422ai.shumi/mcp
Crypto market intelligence: prices, funding rates, narratives, regime, and delta-neutral research.
clean——
24.0
423Signal8
SEC filings, dilution, insider & institutional ownership, and political-trade data for AI agents.
clean——
24.0
424Signal Nodus SEC Filings
Amendment-safe 10-K/10-Q section diffs, claim checks vs XBRL, 8-K events. Accuracy published.
clean——
24.0
425SkillTotal
Deterministic security scan of MCP servers, agent skills and npm/PyPI packages. Runs locally.
clean——
24.0
426Skylit
Options flow, volatility, dealer positioning (GEX) and dark pool data for AI trading agents.
clean——
24.0
427Stratum MCP
Structured execution for coding agents: contracts, postconditions, gates, guardrails.
clean——
24.0
428smry Product
Read public sources and manage a smry library, feeds, notes, highlights, files, and page monitors.
clean——
24.0
429ai.snapdiff/mcp
Visual-diff & change-detection tools that catch agentic UI drift for coding agents.
clean——
24.0
430SnapHost
Send a live, private link to a client from Claude. Updates in place, viewers by email.
clean——
24.0
431ai.sovantica/engrava
MindQL queries, hybrid search, and a thought graph - read/write memory for AI agents.
clean——
24.0
432Spala Public MCP
Discovery, OAuth, project operations, and exact project MCP handoff for Spala backend projects.
clean——
24.0
433SpecStream
Give your agent finished lists from the live web: every row with its source, priced per match.
clean——
24.0
434ai.spelunking/hub
Structure for hard AI decisions, and a human to escalate to when the structure runs out.
clean——
24.0
435SpicyGen
AI adult image, character and movie generator (18+). Characters, images, videos, movies, credits.
clean——
24.0
436Spiderbrain
Deterministic context layer for your codebase: change impact, blast radius, answers with receipts.
clean——
24.0
437ai.spideriq/leads
SpiderIQ Leads: lead-gen MCP (jobs, campaigns, IDAP, Maps, People, Verify, company intel, spiderPR)
clean——
24.0
438ai.ssid/ssid-mcp
Router default logins, compliance index, MAC/OUI lookup. Reads free; submit_correction is Pro.
clean——
24.0
439ai.starreel/starreel
Turn a script into a finished, downloadable short-drama episode — via MCP or REST.
clean——
24.0
440ai.starsinger/starsinger-mcp
Make a finished AI song with real vocals from a brief, or search and stream StarSinger's AI catalog
clean——
24.0
441Python Code Validator
Proves AI-generated Python does what you asked: lint, types, security, sandbox run, exact fixes.
clean——
24.0
442Sugra API
Gateway between LLM agents and world data through eight tools and a bundled endpoint catalog.
clean——
24.0
443Surfing Dog Inbox
Message, ask for a quote or book a call with Surfing Dog, through its open-source inbox.
clean——
24.0
444Switchbooks
Bookkeeping and accounting: P&L, balance sheet, cash flow, transactions, accounts, payees, rules.
clean——
24.0
445Synchronex
Connect any AI agent to your Synchronex workspace — portable memory, decisions, and workers.
clean——
24.0
446ai.syntheticbrew/syntheticbrew
Embed an AI chat widget on your website from your coding agent: provision, configure, get snippet.
clean——
24.0
447ai.takara/miru
Hybrid semantic and keyword code search for coding agents.
clean——
24.0
448Tanvo
AI photo, video and song apps plus image, video and music generation on Tanvo (tanvo.ai).
clean——
24.0
449TargetWise — B2B Prospecting & Enrichment
Find companies and B2B contacts, enrich profiles, and look up work emails and business phones.
clean——
24.0
450Taskfolk
Project management for teams and their AI agents.
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.