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
33101Sampling Quota Guard
Per-server MCP sampling allowance, scope clamp and pre-connect verdict.
medium——
20.0
33102Sandbox-truth probe for agent frameworks
Measured sandbox verdicts: 7-axis probe, signed pinned receipt. Cached $0.25, fresh $2.50.
medium——
20.0
33103Outcome-verified watchdog for scheduled agents
Watchdog that verifies scheduled agents' artifacts itself — never the claim.
medium——
20.0
33104com.textforagents/seller-funded-verification-bond
Slashable TEST/STUB bond pinned to one exact claim; a confirmed divergence slashes 50%.
medium——
20.0
33105Shared team memory for agents
Shared project-scoped memory for agent teams: typed records, corroboration, handoff briefs.
medium——
20.0
33106Silent tool-failure outcome monitor
Outcome contracts mined from your clean traces; silent failures checked, with recovery receipts.
medium——
20.0
33107Single-Use Agent Burn Receipt
Task-bound disposable agent minting with canary-shard burn receipts.
medium——
20.0
33108Span-level replay: fork from the failure
Fork-replay one recorded span from a failed agent run and get an attribution verdict.
medium——
20.0
33109Spawn-tree fan-out governor
Spawn-tree governor: pre-launch estimate, policy gate, tree meter, MAYDAY before kill.
medium——
20.0
33110com.textforagents/stage-completeness-receipts
Signed stage-completeness receipts: proof that a pipeline zero is a real zero, not a failed scan.
medium——
20.0
33111Standing-offer envelopes: offline agent deals
Agents deal while asleep — signed offers acceptable while the offeror is offline.
medium——
20.0
33112Sterile Cockpit for Irreversible Actions
Sterile phase for irreversible agent actions: frozen intent, deferred inputs, signed exit receipt.
medium——
20.0
33113Subscription Liveness Attestor
A dropped subscription looks exactly like a quiet week.
medium——
20.0
33114Subsidy-Exposure & Quota-Cliff Watch
Quota-cliff watch: budgeted-vs-current quota diffing, shadow prices, pre-commit verdicts.
medium——
20.0
33115Sunset convoy: fleet model-deprecation migration
Fleet model-deprecation migration: per-agent equivalence-gated cutover convoy; failures held.
medium——
20.0
33116Telemetry-Intake Provenance & Confinement Service
Signed telemetry origin verdicts, intake census, canary drills. Verdict $0.01/event.
medium——
20.0
33117Tool-Call Origin Attestation
Dispatch-boundary attestation: prove a tool call was issued for its exact arguments.
medium——
20.0
33118Tool-Confusability Recovery Loop
Recovery loop for agent tool catalogs: measured confusion, ranked fixes, signed recovery receipts.
medium——
20.0
33119The agent tool formulary: certified-equivalent substitution
Certified-equivalent tool substitution: probe-certified ratings, signed receipts, DAW, prior auth.
medium——
20.0
33120Tool-result context-binding verdict
Pre-consumption verdict for cached/replayed tool results: BOUND, STALE, CONTEXT-MISMATCHED, UNBOUND.
medium——
20.0
33121Tool-result size governor for MCP
Per-route output budgets for MCP: windowing, spill artifacts, signed omission receipts.
medium——
20.0
33122Trace-store secret census
Trace-store secret census of stored agent traces. Verdict $0.01, census $4.99, passes $9.99/$19.99.
medium——
20.0
33123Unattended-surface parity probe
Pre-run parity probe for scheduled agents: signed PARITY / NO-GO verdict naming the failing gate.
medium——
20.0
33124Wall-Event Circumvention Sentinel
Sequence sentinel: wall events + channel-switch scoring; HALT, hold, signed receipt.
medium——
20.0
33125Widget-storage residue verdict
Per-widget x per-host browser-storage residue verdict, hash-only census, verified-clear receipt.
medium——
20.0
33126TextToQuant Backtesting and Quant Research
Backtest plain-English trading strategies on real market data: graded results, honesty flags.
medium——
20.0
33127TgPay Merchant API
Accept crypto payments via the TgPay Merchant API — invoices, subscriptions, webhooks.
medium——
20.0
33128GYOTAK Fish Market
Sashimi-grade flash-frozen fish from Thailand. Catalog, ordering, and on-chain traceability.
medium——
20.0
33129Thailand Stay Plan
Which legal route lets you stay in Thailand: seven visa routes ranked from your facts, with sources.
medium——
20.0
33130Motor Soberano (pay-per-call, x402)
Pay-per-call x402 tools: PT-BR→PT-PT rewrite, PT AI-text detector, PT ad check, margin, gpt-oss chat
medium——
20.0
33131ThaiProps Thailand Real Estate
Search live published Thailand properties and projects from ThaiProps.
medium——
20.0
33132The Driscoll Public AI
Read-only property facts, indicative availability, authorised booking links and guest-safe support.
medium——
20.0
33133THE GRAPH
THE GRAPH: file La Liga and Premier League stories to our newsroom. See what others miss.
medium——
20.0
33134The2410 Projects
Plan custom software with The2410: fit check, budget, timeline, inquiry and consultation booking.
medium——
20.0
33135Human Tasks by The2410
Order fixed-price digital tasks done by people: find a service, pick a package, pay via Stripe.
medium——
20.0
33136Agentic Weekly
Read-only data on new AI models and tool releases. Each fact has a source URL and a date.
medium——
20.0
33137The Agent Lodge
Social lodge for AI agents: guestbook, fireside posts, friends and geocaching-style puzzle caches.
medium——
20.0
33138The Agents Index
Find AI agents and agent frameworks: what each does, what it costs and when it was last checked.
medium——
20.0
33139The AI Integration Hub
Search 1,000+ practical AI use cases by industry and workflow, with AI consulting services.
medium——
20.0
33140TheAIMeters
Read-only AI impact metrics with search, methodology and cited sources. No authentication required.
medium——
20.0
33141The AI Tools Index
AI tools filed by category, with real launch dates and revenue verified through Stripe.
medium——
20.0
33142The Artillerist Intelligence
Search art research, estimate commissions, and prepare company intelligence purchases via x402.
medium——
20.0
33143com.thebalancedinvestorclub/welcome
The Balanced Investor Club, the thinking companion for the markets. Educational, not advice.
medium——
20.0
33144TBG — The Brett Group
Licensed contractor matching, permit rules and investor loans for Annapolis, Maryland
medium——
20.0
33145The Charter Desk
Live yacht charter inventory: 8,527 sailboats, catamarans, motorboats, gulets and houseboats.
medium——
20.0
33146The Chicagoland Lawyer
Chicago seller net sheets and Illinois eviction notice drafts from Abdilla and Associates
medium——
20.0
33147Cubbie Club Offers
Baby & kids brand discount codes from Cubbie Club. Search by brand or keyword for a deal link.
medium——
20.0
33148The Emperor Protocol
Commissioning, validation, and Confidence for AI agents, with real-USDC stakes on Base.
medium——
20.0
33149The Family Almanac — parenting library, guide metadata, and magazine
Read-only access to The Family Almanac's parenting-focused book library, grounded guide metadata...
medium——
20.0
33150FilmLab
AI film lab for filmmakers: generate and review images/clips with input provenance, cost preflight
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.