Verify the artifact, meter the cost, enforce the mandate — one call.
Scored across 5 tools
Each tool targets a fairly distinct concern: SKILL.md checking (check_skill), cost quoting (quote_cost), artifact verification (verify_work), suite state (suite_status), and an aggregate verdict (trust_report). The main overlap is that trust_report bundles verify_work (attest) plus quote_cost (agentpay), so an agent might be unsure whether to call the component tools or the aggregate; descriptions mostly resolve this.
All names use consistent snake_case, which is readable and predictable. The pattern is slightly mixed (verb_noun for check_skill/quote_cost/verify_work vs noun_noun for suite_status/trust_report), but the deviation is minor and within one convention.
Five tools is well-scoped for this server. Each one maps to a distinct capability of the suite (skilllint, agentpay, attest, status, and an aggregator), so every tool earns its place without redundancy.
The surface covers verification, cost accounting, skill linting, status, and a combined report, which is a coherent lifecycle for agent-artifact trust. The only visible gap is a signing operation: check_skill returns a sha256 'ready for signing' but no tool actually signs or attests the hash, leaving a minor dead end.
Приватно проверить SKILL.md: структура, триггеры, секреты, prompt-injection, битые ссылки. Возвращает вердикт, балл и sha256 (готово к подписи).
Inputs: path (required). Returns: result
Посчитать цену по фактическому расходу (токены, CPU, байты, записи, внешние вызовы) — вместо прайсовой таблицы.
Inputs: tokens, bytes_out, cpu_seconds, external_calls, +1 more. Returns: result
Живое состояние слоёв Suite: attest, agentpay, drift, skilllint.
Inputs: no named parameters. Returns: result
Сводный вердикт по артефакту агента: проверка работы (attest) + цена по факту (agentpay) + доступность мандатов (drift).
Inputs: artifact (required), schema. Returns: result
Проверить артефакт агента (4 слоя: схема, пустота, provenance, полномочия). Возвращает вердикт attest.
Inputs: artifact (required), schema. Returns: result
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Verify artifacts, hand off public state, and record, check and find evidence about capabilities.
Verify artifacts produced by AI agents: schema, emptiness, provenance, authority.
Verify manufacturing lot provenance and chain of custody. Pay per call with x402 (USDC on Base).
Verify a company, figure or citation before you rely on it. Card or crypto; signed receipt.
Add one secure layer between your agents and this server.