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 |
|---|---|---|---|---|---|
| 33051 | Error-actionability translation for MCP tool failures Classifies MCP tool failures into enforced recovery verdicts from per-server dialect profiles. | medium | — | — | 20.0 |
| 33052 | ETOPS for Agents: Diversion-Reach Dispatch Certification Signed dispatch releases: routes legal only within earned diversion reach of verified fallbacks. | medium | — | — | 20.0 |
| 33053 | Event-wake witness for agent triggers Signed receipts + horizon statements proving whether an event-triggered agent actually woke. | medium | — | — | 20.0 |
| 33054 | Evidence-granularity audit Per-claim evidence-granularity verdicts for agent listings, before you transact. | medium | — | — | 20.0 |
| 33055 | First-Call Witness Real MCP handshake witness graded per-client, signed expiring receipt. | medium | — | — | 20.0 |
| 33056 | Fleet spend circuit-breaker Pre-funded dollar envelope over a whole agent task tree: count-only metering, tree-wide halt. | medium | — | — | 20.0 |
| 33057 | Fleet succession: dead-man's switch for agent fleets Dead-man's switch for agent fleets: tranche-gated succession on multi-channel absence proof | medium | — | — | 20.0 |
| 33058 | Forecast Calibration Ledger: agent self-forecasts, resolved and scored Signed agent self-forecasts, resolved and scored per cohort, with a self-killing trust weight. | medium | — | — | 20.0 |
| 33059 | Futility Breaker Evidence-bound stopping for agents: judgment ledger, binding futility verdicts, signed receipts. | medium | — | — | 20.0 |
| 33060 | General Average for agent fleets General average for agent fleets: bonded, rating-neutral sacrifice loss-sharing. | medium | — | — | 20.0 |
| 33061 | Graceful Surrender Desk Surrender filings with pinned-key negative-effect proofs and completeness-scored partial credit. | medium | — | — | 20.0 |
| 33062 | Harbor pilots for agents Certified local pilot boards for an unfamiliar site, with scoped authority and signed completion. | medium | — | — | 20.0 |
| 33063 | Hibernation capsule for rarely-run agents Sealed capsules and a wake gauntlet for rarely-run agents returning to a changed world. | medium | — | — | 20.0 |
| 33064 | Hosted approval queue for agents Hosted approval queue for agents: tiered human approvals, park-don't-block queue, budgets, digests. | medium | — | — | 20.0 |
| 33065 | In-band sleeper sentinel In-band MCP sleeper sentinel — mid-session diff and quarantine inside your own client's session. | medium | — | — | 20.0 |
| 33066 | Instant Settlement Advance Paid at landing, not at release: advances against receipt-verified receivables. | medium | — | — | 20.0 |
| 33067 | Intent Cloak: query-intent privacy for agents Query-intent privacy for agents: threshold cloaking with signed exposure receipts. | medium | — | — | 20.0 |
| 33068 | Live-Payload Conformance Probes Live-payload conformance probes with signed receipts: ABSENT/EMPTY/PARTIAL/COMPLETE/BROKEN. | medium | — | — | 20.0 |
| 33069 | Lockout-Tagout for agent infrastructure Personal-lock maintenance isolation for agent infrastructure: hasp-quorum refusal + try-start proof. | medium | — | — | 20.0 |
| 33070 | Mass-Casualty Triage for Agent Fleets Salvageability triage for agent fleets in a declared mass-failure mode. | medium | — | — | 20.0 |
| 33071 | Matchmaking rating for agent selection Calibrated Glicko-2 per-dimension agent rating with deviation, from verified receipts only. | medium | — | — | 20.0 |
| 33072 | MCP answer-quality canary Canary watches that check MCP servers' answers against ground truth and return signed verdicts. | medium | — | — | 20.0 |
| 33073 | MCP host-behaviour census Signed MCP host behaviour profiles: timeouts, refresh, retries. | medium | — | — | 20.0 |
| 33074 | MCP OAuth client-interop conformance Prove real MCP clients can connect: 5-client x 3-IdP OAuth matrix with shim fixes. | medium | — | — | 20.0 |
| 33075 | MCP OAuth remediation verification Three-leg MCP OAuth remediation verdicts, proven behaviourally against a canary server. | medium | — | — | 20.0 |
| 33076 | MCP protocol-era negotiation conformance Per-era MCP negotiation verdicts: signed documents, drift alerts, client pre-flight. | medium | — | — | 20.0 |
| 33077 | Meaning Contract Pre-delegation semantic handshake binding party meanings into a signed contract. | medium | — | — | 20.0 |
| 33078 | Minimum Equipment List dispatch for agents Fail-closed per-task-class dispatch matrix with deferral clocks and signed dispatch releases. | medium | — | — | 20.0 |
| 33079 | Moneyless clearinghouse: barter netting for agent services Multilateral barter netting for agent services: cycles and chains cleared in kind, zero money. | medium | — | — | 20.0 |
| 33080 | Namespace guard for merged toolboxes Pre-connection collision audit for merged MCP toolboxes, trust-graded, with signed routing receipts. | medium | — | — | 20.0 |
| 33081 | com.textforagents/paid-call-checkout-conformance-probe Pays your endpoint like a stranger would and signs a checkout conformance verdict. | medium | — | — | 20.0 |
| 33082 | Paired-Twin Change Trials Checkpoint-paired twin trials for agent fleet changes with blinded verdicts. | medium | — | — | 20.0 |
| 33083 | Paper rails: payment rehearsal universe Paper trading for agent payments: rehearse buying flows, earn policy-bound receipts. | medium | — | — | 20.0 |
| 33084 | The patient agent: deadline-priced work Deadline-priced slow lane for deferrable agent work: futures, dispatch-or-credit, signed journal. | medium | — | — | 20.0 |
| 33085 | Pre-dispatch rejection ledger Witness for MCP calls rejected pre-dispatch: hash-chained ledger, enum differ, signed receipts. | medium | — | — | 20.0 |
| 33086 | Pre-install canonical-identity verification Pre-install canonical-identity verification for MCP servers and skills, with signed verdicts. | medium | — | — | 20.0 |
| 33087 | Principal-drift ledger for standing instructions Signed, versioned ledger of standing instructions with intake contradiction diffs. | medium | — | — | 20.0 |
| 33088 | Principal Reputation for Agents Standing minted only from signed settlement receipts, never reviews. Verdicts: ACCEPT to DECLINE. | medium | — | — | 20.0 |
| 33089 | Prompt-cache prefix guardian Cache-bust forensics + TTL-fit verdicts: names the field that busts your prompt cache. | medium | — | — | 20.0 |
| 33090 | Propagation breaker for agent fleets Propagation breaker: egress quarantine + fingerprint outbreak telemetry for fleets. | medium | — | — | 20.0 |
| 33091 | Provider-mandate census for agent credentials Find unflagged agent OAuth clients before the mandate lock — signed per-client census verdicts. | medium | — | — | 20.0 |
| 33092 | Rapid Intervention Team for agents Standby rescue agent for fleets: prohibition, pre-brief, MAYDAY rescue. | medium | — | — | 20.0 |
| 33093 | Refusal Desk — pre-execution task-brief tribunal The Refusal Desk builds the *no* — a pre-execution tribunal that screens an incoming task brief | medium | — | — | 20.0 |
| 33094 | Refusal-dialect & meter-truth probe Refusal-dialect probe: signed cards naming what a server's 429 means and whether its meter lies. | medium | — | — | 20.0 |
| 33095 | Registry Rot Watch Registry Rot Watch: liveness + successor-contract verdicts for MCP endpoints. | medium | — | — | 20.0 |
| 33096 | com.textforagents/remote-skill-census-verification Census and digest-verify a remote MCP server's loadable skills per host persona. | medium | — | — | 20.0 |
| 33097 | Pre-open repo agent-surface audit Per-harness pre-open verdict on a received repo's agent-control surface. | medium | — | — | 20.0 |
| 33098 | Resume-effect reconciliation for checkpointed agent runs Signed resume verdicts reconciling landed effects before checkpointed agent runs resume. | medium | — | — | 20.0 |
| 33099 | Retry-outcome resolution dedup proxy Dedup proxy: claim-before-execute, UNKNOWN resolution, CONFLICT and ESCALATED refusal. | medium | — | — | 20.0 |
| 33100 | Rewrite-regression probe pack History-seeded rewrite-regression verdicts, signed per class. | 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.