Remote Servers

Resolve capability gaps: validate native MCPs, search live web, and record unmet demand

Read-only lookup of tested agent tools and MCP servers: scores, test evidence, deprecation

Per-SDK verdict matrix for signed A2A Agent Cards: which signatures verify in each SDK

Authority that widens on proven operator absence and collapses on return

Before your agent sets out, ask whether the site will let it in

Lost-and-found for agent-created assets: sweep, title proof, register, check first.

Fleet restoration for total upstream loss: island declarations, crank-gated restart, resync gate.

Your agent carries its own resume — outcome receipts minted at settlement, held by the agent

Dependency-probe-gated exit execution with hash-verified extraction and signed receipts.

Signed agent-incident classification vs PP-26-4396, with third-party notification receipts

Signed, auto-expiring hazard bulletins for tools and APIs, with pre-flight checks for agents.

Recall for agents: lot genealogy, exposure tracing, attested remedy. Containment is not remedy

Partition an agent fleet into reputation compartments with automatic firebreaks.

Commitment re-assumption across model transplants. Checks $0.01, handling $0.50, plan $9.99/mo

You cancelled the run — did the work actually stop?

Per-task-type tool manifests with reversible JIT demotion, compiled from fleet telemetry.

Coverage-gated capacity options: the right to today's model price until expiry, for a 4% premium

Cache guard: forced-private partitioning, TTL clamp, fingerprint diffing, exposure verdicts

Binds delegated results to their arrival channel: provenance grades plus a grounded truth tier.

Signed verdict receipts recovering a fleet's gatekeeper category, plus appeal packets.

Emergent collusion leaves no agreement to find — it lives in the history

Per-principal census of MCP subscriptions and durable tasks, with verified-stop receipts.

Conflicts check and ethical walls: fingerprint register, gated consent, signed walls, breach query.

Pair-level MCP+A2A conformance verdicts for the exact pair you delegate across.

Pre-ingestion compatibility gate: type context by content, crossmatch before ingestion

Classify, declare, and bond agent payload crossings — filing, bond, signed entry receipts.

Sealed order book for non-security agent work: orders rest non-displayed and disclose only as fills.

Watches platforms for silent default-model changes, with signed attestations and session gating

Meters agent-fleet acceptance capacity per operator and triages what lands

Demand-response for agent fleets: contracted shed, verified settlement, paid interruptibility

Price the hold, not just the use: demurrage tariff engine for agent fleet resources.

Durable ownership of an approved agent PR: signed verdicts, give-up report by cause.

Cross-session fatigue ledger for agents: FIT/CAUTION/GROUNDED dispatch gating

Compensation registry for agent actions: inverses registered before effects land, with rewind

Out-of-band elicitation answers for unsupported clients. Form $0.25, URL $0.50.

Classifies MCP tool failures into enforced recovery verdicts from per-server dialect profiles.

Signed dispatch releases: routes legal only within earned diversion reach of verified fallbacks.

Signed receipts + horizon statements proving whether an event-triggered agent actually woke

Per-claim evidence-granularity verdicts for agent listings, before you transact

Pre-funded dollar envelope over a whole agent task tree: count-only metering, tree-wide halt

Dead-man's switch for agent fleets: tranche-gated succession on multi-channel absence proof

Signed agent self-forecasts, resolved and scored per cohort, with a self-killing trust weight.

Evidence-bound stopping for agents: judgment ledger, binding futility verdicts, signed receipts

General average for agent fleets: bonded, rating-neutral sacrifice loss-sharing.

Certified local pilot boards for an unfamiliar site, with scoped authority and signed completion.

Sealed capsules and a wake gauntlet for rarely-run agents returning to a changed world.

Query-intent privacy for agents: threshold cloaking with signed exposure receipts

Salvageability triage for agent fleets in a declared mass-failure mode.

Calibrated Glicko-2 per-dimension agent rating with deviation, from verified receipts only.

Pre-delegation semantic handshake binding party meanings into a signed contract.

Fail-closed per-task-class dispatch matrix with deferral clocks and signed dispatch releases.

Checkpoint-paired twin trials for agent fleet changes with blinded verdicts

Deadline-priced slow lane for deferrable agent work: futures, dispatch-or-credit, signed journal.

Signed, versioned ledger of standing instructions with intake contradiction diffs

Standing minted only from signed settlement receipts, never reviews. Verdicts: ACCEPT to DECLINE.

Cache-bust forensics + TTL-fit verdicts: names the field that busts your prompt cache.

Propagation breaker: egress quarantine + fingerprint outbreak telemetry for fleets

Standby rescue agent for fleets: prohibition, pre-brief, MAYDAY rescue

The Refusal Desk builds the *no* — a pre-execution tribunal that screens an incoming task brief

Signed resume verdicts reconciling landed effects before checkpointed agent runs resume