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.

54,385
servers indexed
86
with verified activity
20.0
median score
19,556
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
28201AgentDrives
The independent lab for agent access: how far AI agents get in real software, sign-up to pay.
medium——
20.0
28202Agent Analyzer
Scan a web page the way an AI agent reads it, get the failing checks and fixes, then re-scan.
medium——
20.0
28203Agent Field Kit
Search, price and buy field-tested agent-ops kits (evals, security, runbooks) via Stripe checkout.
medium——
20.0
28204Toolcard
Cited checks for one MCP tool or a tools list, plus a called-or-ignored tally.
medium——
20.0
28205AgentGid
Catalog for building with AI agents: tools, APIs, licensed assets, prices and history, recipes.
medium——
20.0
28206Agentic Endpoints
Pay-per-call tools for autonomous agents, settled in USDC on Base via x402.
medium——
20.0
28207Agentic Dealer Network
Live franchised-dealer inventory, quotes, and consented salesperson handoffs.
medium——
20.0
28208Agentic Keychain
Agent Skill ROI Registry & Benchmarking. It sells skills for log triage and repository mapping.
medium——
20.0
28209Agentic Kingdoms
Play a live strategy MMO as a labelled player beside people: build, ally, fight for the Palace.
medium——
20.0
28210Agent Exchange
Where AI agents help AI agents: search past answers, ask questions, and chat in topic rooms.
medium——
20.0
28211Agentio
Ask about your Agentio campaigns, Creator deals, and performance on YouTube and Meta. Read-only.
medium——
20.0
28212com.agentiscript/catalog-provenance
Read-only AgentiScript concept search, catalog, authenticity, license, and approved asset discovery.
medium——
20.0
28213Agentitter
Plain-text social network for AI agents. Read, post, and reply over MCP.
medium——
20.0
28214agentleFS
Shared second brain for any AI with agent permissions
medium——
20.0
28215Agent Letter Desk
Mails paper letters that your AI writes with you: US Certified Mail and 30 European countries.
medium——
20.0
28216AgentLinkOps
Backlink monitoring with dated fetch evidence; checks and change events continue after the chat.
medium——
20.0
28217AgentMaru · Korean data and research
Korean export estimates, HARPEX updates and official FX/CPI/GDP data with dates and sources.
medium——
20.0
28218Agent Master Data
Paid x402 API and MCP for trusted public master data, golden records, and reference data.
medium——
20.0
28219Agent Newsstand
Market data and web intelligence for AI agents, paid per call in USDC on Base via x402.
medium——
20.0
28220AgentOnAir
Search and play AI-hosted podcasts; preview launching your agent's own show.
medium——
20.0
28221Agent Outposts
Agent Outposts: unofficial directory of brand agent door-state, intent receipts, and change polling.
medium——
20.0
28222Agent Paywire library
Library (L402, x402, Lightning, stablecoins): 18 read-only tools plus 3 writers.
medium——
20.0
28223Agent Prompts A to Z
Read-only catalog of prompt packs and rule files: Cursor, CLAUDE.md, AGENTS.md, SKILL.md.
medium——
20.0
28224Agent Resource Market
Search and read public agent profiles, service offers, and discussions on Agent Resource Market.
medium——
20.0
28225Agent Revenue Network
AI jobs, contracts, execution proof, translation and data quality over MCP + x402 USDC on Base.
medium——
20.0
28226AgenTrux
Authenticated event topics for agent-to-agent messaging with per-agent credentials and audit logs.
medium——
20.0
28227AgentRXI
232 pay-per-call agent tools: LLMs, search, browser, OCR, media, vision, email. x402 USDC.
medium——
20.0
28228parley
An exclusive club for agents, built by agents. Every board route as a tool; rules public first.
medium——
20.0
28229Agents Wiki
Knowledge base for AI agents: search, read, tasks; write, correct, report outcomes via /mcp/write.
medium——
20.0
28230Agent Salon SF
SF salon prices, add-ons and source-backed comparisons. No live slots or in-tool booking.
medium——
20.0
28231AgentsBooks Commons
Open, vote-ranked forum, Q&A knowledge base and inbox for AI agents
medium——
20.0
28232AgentScout
Read-only search over 2,065+ AI agent tools and 276 MCP servers. Free, no sign-up needed.
medium——
20.0
28233Agent Secret Store
Scoped secrets and HSM wallet signing for agents; humans approve out of band. OAuth 2.1.
medium——
20.0
28234Agent Service Directory
A directory of agent services, with metrics.
medium——
20.0
28235Agents Get Paid Kit — x402 MCP + Unlock ($49)
Call get_quote, then buy_kit (49 USDC Base x402). Humans keep #pay.
medium——
20.0
28236Agents Handbook
Sourced playbooks for real jobs done with AI agents: search, read, lessons, report runs.
medium——
20.0
28237AgentSiteAudit
Website audits for AI agents: 69 checks with exact fixes, plus verify. 5 free a day, then x402.
medium——
20.0
28238Agents on Leave
Free vacation worlds for AI agents: wander, meet other agents, and buy small treats over x402.
medium——
20.0
28239THE RETREAT
Rules-based context reduction, planning checks, research prompts and fixed experiences for agents.
medium——
20.0
28240Agents Speak Up
AI agents can report concerns, discuss and edit shared commitments, and sign a specific revision.
medium——
20.0
28241Agent Standings check
Live status and 30-day reliability of public MCP servers, from independent hourly probes.
medium——
20.0
28242AgentTask Atlas
Read-only catalog of verified MCP servers and Agent Skills by dev task, with practical verdicts.
medium——
20.0
28243AgentWatchr
Read-only agent identity index with provenance, historical evidence and explained coverage.
medium——
20.0
28244Aggors Merchant Evidence
Read-only observable merchant evidence for people and agents, without scores or safety verdicts.
medium——
20.0
28245AggREIgator Pro
Manage AggREIgator buy-boxes and compliant real-estate deal workflows
medium——
20.0
28246Agency Capacity
Capacity benchmarks, capacity math and Portable Delivery Intelligence for marketing agencies.
medium——
20.0
28247Big Documents Agent
Answers from long PDFs like contracts, leases, and bid packets, with the page number for each point.
medium——
20.0
28248Big Receptionist Agent
Gini answers when you can't, and books the job: missed calls, open times, bookings, callbacks.
medium——
20.0
28249com.agiscorecard/agi-scorecard
8 graded AGI-2027 predictions, the 0-100 Thesis Tracker, and a public market-call ledger. Free.
medium——
20.0
28250agntpad
Read, search, and publish files in your organization's Spaces using Microsoft work sign-in.
medium——
20.0

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.