Rewrite-regression probe pack
Server Details
History-seeded rewrite-regression verdicts, signed per class.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-03-26
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 4 tools
The tool set splits into a metadata tool (rewrite_family), an execution tool (rewrite_pack), a precomputed-result tool (rewrite_verdict), and a signature checker (rewrite_verify_pack). The three 'pack/verdict' tools share vocabulary and could be confused at a glance, though the descriptions do draw the run-vs-precomputed-vs-verify distinction reasonably well.
All names use a consistent rewrite_ prefix and snake_case, which is predictable. Minor deviation: three tools are rewrite_<noun> while rewrite_verify_pack inserts a verb, so the verb/noun pattern isn't uniform.
Four tools is a tight but coherent scope for a focused rewrite-regression probe pack (discover, run, fetch verdict, verify). Nothing is redundant, though the surface is on the thin side and leaves little room for adjacent operations.
The core lifecycle is covered: enumerate the advisory family, run a pack against a candidate, retrieve a signed verdict, and verify a signed pack against the pinned key. Gaps are minor — no tool for billing/pass status checks or listing prior pack runs/results, which agents would otherwise have to work around.
Available Tools
4 toolsrewrite_familyCInspect
The launch advisory family: 5 shapes with classes and advisories.
Inputs: no named parameters.
rewrite_packCInspect
Run a rewrite-regression pack against an authorised candidate (house_double or target_url+authorised+authorisation). Trial/pass/x402 billing as on POST /pack.
Inputs: rounds, payment, authorised, target_url, +2 more.
rewrite_verdictDInspect
Precomputed signed per-class verdict by candidate fingerprint ($0.01 x402 or pass).
Inputs: fingerprint (required), payment.
rewrite_verify_packCInspect
Verify a signed pack against the pinned production signing key.
Inputs: pack (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Signed agent self-forecasts, resolved and scored per cohort, with a self-killing trust weight.
Sealed prediction-market verdicts, graded in public across Polymarket and Kalshi. No auth required.
Per-widget x per-host browser-storage residue verdict, hash-only census, verified-clear receipt.
Signed telemetry origin verdicts, intake census, canary drills. Verdict $0.01/event.
Related MCP Servers
AlicenseAqualityAmaintenanceSigned, append-only record of the decisions behind a coding agent's work, kept in the repository. Agents record each decision with its reasons and the alternatives turned down, and read the decisions in force before they edit; the record verifies offline.275Apache 2.0- AlicenseNot gradedqualityBmaintenanceVerifies bernstein run receipts and hash chains by recomputing embedded chains, checking signatures, and returning signed verdicts.Apache 2.0
- AlicenseAqualityBmaintenanceEnables agents and security automation to adjudicate proposed defense mutations against a sealed, canonicalized attack scenario, enforcing reproduction, impact-screening, regression, and proven-improvement gates before promoting at most one candidate. Every verdict, rejected candidate, and rejection reason is sealed into a recomputable SHA-256 Merkle evidence root and hash-linked lineage that can be independently verified without trusting the server.6MIT
- AlicenseBqualityCmaintenanceVerify a number before an agent asserts it — a Deflated Sharpe Ratio for backtest, plus eval-gap, subset-win, and judge-bias checks, with signed receipts anyone can verify offline.34MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.