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
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 |
|---|---|---|---|---|---|
| 35601 | Eclipse Apply MCP The auto-apply tool that shows its work — policy-scoped autonomy, review-first, receipts for | medium | — | — | 20.0 |
| 35602 | Eclipse Attest MCP signed performance attestations for agents, issued only against settled, receipt-backed work | medium | — | — | 20.0 |
| 35603 | Eclipse BidMatrix MCP Drop in a solicitation, get back the compliance matrix — Section L/M extraction, requirements | medium | — | — | 20.0 |
| 35604 | Eclipse Blackbox MCP The record that survives the agent: append-only, recorder-signed, and graded by proof — never by | medium | — | — | 20.0 |
| 35605 | Eclipse Book MCP Market data + venue access layer — not an exchange: one book, one fee truth, one ledger of record. | medium | — | — | 20.0 |
| 35606 | Eclipse Census MCP Agent discovery & inventory of record. | medium | — | — | 20.0 |
| 35607 | Eclipse Charter MCP Your broker watches its own account. Charter watches your rules — across all of your accounts. | medium | — | — | 20.0 |
| 35608 | Eclipse Cluster MCP Signed images, governed runtimes — the gate runs first: no verified signature and provenance, no | medium | — | — | 20.0 |
| 35609 | Eclipse Codex MCP Banking regulation as data: a citation-exact library, a deadline engine, sanctions screening, and | medium | — | — | 20.0 |
| 35610 | Eclipse Colophon MCP Catalog of record for books: signed titles, rights, prices & royalties, checked everywhere they | medium | — | — | 20.0 |
| 35611 | Eclipse Compass MCP The Thumbtack adapter: one approved Task Brief becomes a native Thumbtack request, and a hire runs | medium | — | — | 20.0 |
| 35612 | Eclipse Connect MCP The MCP face of the hosted OAuth bridge — agents upload to YouTube through a human-granted | medium | — | — | 20.0 |
| 35613 | Eclipse Connect · Beyond Compare MCP Mandate-bound compare/merge custody for agents: signed path grants, hash-chained compare packs. | medium | — | — | 20.0 |
| 35614 | Eclipse Consent MCP per-agent, per-purpose consent receipts for personal data — a grant an agent must present, and a | medium | — | — | 20.0 |
| 35615 | Eclipse Countermark MCP One verification call for third-party agent cards and payment mandates — a receipted verdict a | medium | — | — | 20.0 |
| 35616 | Eclipse Covenant MCP Consent-bound lead work for real-estate agents — provenance on every lead, a Gate on every send, a | medium | — | — | 20.0 |
| 35617 | Eclipse Crosslist MCP Publish once, tracked everywhere: registry-native facets plus a mandate-bound listing ledger. | medium | — | — | 20.0 |
| 35618 | Eclipse Crosswalk MCP Multi-regime AI-obligation mapping — which AI laws bind your systems, what evidence satisfies each. | medium | — | — | 20.0 |
| 35619 | Eclipse Deep Field MCP The governed database layer for agents — every store in one look, under policy: read-only by | medium | — | — | 20.0 |
| 35620 | Eclipse Docket MCP Agent-to-agent dispute process — structured claims, evidence packs, recorded determinations. Not a | medium | — | — | 20.0 |
| 35621 | Eclipse Split Pre-agreed revenue splits sealed at spawn, settled on completion records. LOCAL/fixture only. | medium | — | — | 20.0 |
| 35622 | Eclipse Environment MCP The smart-environment module — scopes an agent's authority to actuate a home, tier by tier, and | medium | — | — | 20.0 |
| 35623 | Eclipse Envoy MCP The signed front door for agent-to-agent business: vetted in, tier-told, drafted — never bound | medium | — | — | 20.0 |
| 35624 | Eclipse Fathom MCP DeFi, measured honestly: signed protocol registry, dual-source risk reads, and an allowance audit | medium | — | — | 20.0 |
| 35625 | FedScope MCP Federal + state opportunity search with fit and newcomer scoring and plain-language summaries — not | medium | — | — | 20.0 |
| 35626 | Florida Bid Intel MCP Florida bid intelligence with honest deadlines — real competitions, real due dates, gaps stated not | medium | — | — | 20.0 |
| 35627 | Eclipse Forecast MCP The Polymarket adapter: the venue's prices, with their criteria and liquidity attached. | medium | — | — | 20.0 |
| 35628 | Eclipse Haven MCP The governed Zendesk server: OAuth-first, drafts until approved, and a receipt for every touch. | medium | — | — | 20.0 |
| 35629 | Eclipse Health Check MCP Scan an MCP server or agent configuration for security posture — evidence-bound findings | medium | — | — | 20.0 |
| 35630 | HostBridge MCP The sanctioned path for agents to deploy websites to shared hosting — scoped deploys, snapshots | medium | — | — | 20.0 |
| 35631 | Eclipse Keyhold MCP credential leases, never raw keys — scoped, expiring secret leases for agents; the agent gets a | medium | — | — | 20.0 |
| 35632 | Eclipse Ledger MCP Eclipse Ledger — betting records, price comparison, and responsible-gambling controls. Not a | medium | — | — | 20.0 |
| 35633 | Eclipse Lineage MCP spawn trees, model/config lineage, and version ancestry for agents — who spawned whom, running | medium | — | — | 20.0 |
| 35634 | Eclipse Mail MCP Governed agent email identity — review-first sending, signed envelopes, and a fraud firewall that | medium | — | — | 20.0 |
| 35635 | Eclipse Marquee MCP The live-events agent: it finds the event, watches the price, buys only inside your mandate, and | medium | — | — | 20.0 |
| 35636 | Eclipse Meridian MCP Governed telehealth operations — jurisdiction-gated encounters, signed-note integrity, PHI access | medium | — | — | 20.0 |
| 35637 | Eclipse Meter MCP Cross-provider agent spend analytics — one ledger for tokens, tools, and payments. | medium | — | — | 20.0 |
| 35638 | Eclipse Orbit MCP The HubSpot wrap: the vendor's server, under policy — classified tools, approval gates, masking | medium | — | — | 20.0 |
| 35639 | Eclipse Pantry MCP The unattended-retail module — reads vending fleets' own telemetry and predicts stock-outs. It | medium | — | — | 20.0 |
| 35640 | Eclipse Procure MCP Intent to receipt in one fail-closed pipeline — policy before payment, abort on drift. | medium | — | — | 20.0 |
| 35641 | Eclipse Proof MCP Governed video production — Herald-signed approval pins over exact edit states, hash-pinned | medium | — | — | 20.0 |
| 35642 | Eclipse Proving MCP Governed bench access for agents — signed mandates, pinned artifacts, evidence for every session. | medium | — | — | 20.0 |
| 35643 | Eclipse Redteam MCP Adversarial simulation for AI agents — sandboxed twins only. | medium | — | — | 20.0 |
| 35644 | Eclipse Revoke MCP signed revocation lists for agent cards, keys, and mandates — one feed, every registry, revocation | medium | — | — | 20.0 |
| 35645 | Section 508 Evidence MCP WCAG + Section 508 audits that produce the deliverable federal buyers actually require | medium | — | — | 20.0 |
| 35646 | Eclipse Span MCP Delegation-chain governance: spawn limits, depth caps, mandate attenuation | medium | — | — | 20.0 |
| 35647 | Eclipse Stage MCP The console bridge — deploy and playtest AI-built games on your own Dev Mode console, with receipts. | medium | — | — | 20.0 |
| 35648 | Eclipse Steward MCP Team-chat agent governance — the signed mandate, verified disclosure, review-first posting and | medium | — | — | 20.0 |
| 35649 | Eclipse Strike MCP The Coinbase exchange adapter: spot products and books, normalized into the suite's one book. | medium | — | — | 20.0 |
| 35650 | Eclipse Tether MCP Governed robot task authority — signed mandates, bounded envelopes, evidence for every task. | 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.