Futility Breaker
Server Details
Evidence-bound stopping for agents: judgment ledger, binding futility verdicts, signed receipts.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2024-11-05
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 6 tools
Most tools target clearly separate actions: register_run (setup), judge (record), verdict (read), receipt (mint), verify_receipt (validate), waste_report (report). The main friction is futility_judge vs futility_verdict, which sound near-synonymous and only the descriptions clarify that one writes and one reads; futility_receipt vs futility_verify_receipt is close but the verify semantics are clear.
The futility_ prefix is applied uniformly, which is good, but the second segment mixes verbs and nouns: futility_judge, futility_register_run, futility_verify_receipt are verb-style while futility_receipt, futility_verdict, futility_waste_report are noun-style. Readable overall, but not a predictable verb_noun pattern.
Six tools is tightly scoped to a single workflow (register → judge → verdict → receipt → verify → report) with no redundant or filler entries. Each tool maps to a distinct step in the verdict lifecycle.
The core loop is closed: runs can be registered, judged, read, receipted, verified, and reported on. Gaps are enumeration/management operations — no way to list runs, list prior judgments, or amend/revoke a recorded judgment — which agents could work around but would feel if managing many runs.
Available Tools
6 toolsfutility_judgeJudge a resultBInspect
Record one usefulness judgment (useful / useless / partial) for a run/source/domain and return the binding verdict (CONTINUE / STOP-SOURCE / INTEGRATE-NOW / ABSTAIN). Billed as a verdict call: one-time trial, tier allowance, or x402 $0.002.
Inputs: label (required), run_id (required), source (required), query, +2 more.
futility_receiptMint the abstention receiptAInspect
Mint the HMAC-signed abstention receipt when the run/source/domain verdict is ABSTAIN.
Inputs: run_id (required), source (required), domain.
futility_register_runRegister a runBInspect
Register a run with its alternatives and operator-registered source identities (strings or {id, aliases}) before judging.
Inputs: run_id (required), sources, alternatives.
futility_verdictRead the current verdictBRead-onlyInspect
Read the current verdict for a run/source/domain without recording a judgment.
Inputs: run_id (required), source (required), domain.
futility_verify_receiptVerify a receiptCRead-onlyInspect
Verify a receipt payload {receipt, signature}; total rejection with a reason on malformed/forged input.
Inputs: receipt (required), signature (required).
futility_waste_reportWaste report for a runBRead-onlyInspect
Waste report for a run: tokens spent after the verdict point, per source and per domain aggregate.
Inputs: run_id (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Cryptographically anchored evidence for agents: verified run receipts, proof-gated settlement.
Bounded authorization and independently verifiable execution evidence for agents.
Bounded agent exploration with persistent progress, deterministic receipts, and return contracts.
Second opinion before an irreversible agent action; signed proofs, free verify, public ledger.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceCryptographically anchored, tamper-evident evidence receipts for AI agents — verified run receipts, existence-at-time proofs, and cited answers from an anchored public record. Remote MCP with proof-gated settlement; attests existence and integrity, never truth.-

evermint-mcpofficial
AlicenseNot gradedqualityDmaintenanceTamper-evident receipts for AI agent actions. The notary layer for agent-to-agent transactions.40 npm1MIT- AlicenseNot gradedqualityDmaintenanceProvides cryptographic governance receipts for AI agents, enabling pre-execution evaluation and signed verdicts (EXECUTE/BLOCK/REVIEW/SHADOW) with offline-verifiable audit trails.MIT

emilia-mcp-serverofficial
AlicenseAqualityAmaintenanceThe accountability layer for AI agents — a named human's signed yes before an agent does anything irreversible (payment, record change, deploy), then an offline-verifiable Trust Receipt. Apache-2.0, formally verified.3550Apache 2.0
Glama MCP Gateway
Add one secure layer between your agents and this server.