DEPENDENCY EVIDENCE

Know what changed before you depend on it.

For teams using external agents and MCP servers: inspect evidence, watch changes, record what you accepted.

Check a client configuration locally · Agency pilot

archtoolsdev/arch-tools

Runtime observation: 2026-11-08T17:27:07.240473+00:00 · State: partial

Watches availability, tools and schemas, auth access, endpoints and lifecycle notices. Only complete schemas are compared. OAuth scope and consent-screen changes are not measured.

Agent and MCP watches share your plan's budget. Manage watches.

Current recorded evidence

{
  "auth": "anonymous",
  "availability": "partial",
  "endpoint": "https://archtools.dev/mcp",
  "legal_identity": null,
  "lifecycle": null,
  "observed_at": "2026-11-08T17:27:07.240473+00:00",
  "registry_status": null,
  "subject": {
    "id": "archtoolsdev/arch-tools",
    "kind": "mcp"
  },
  "tools": {
    "names": [
      "ai-generate",
      "ai-oracle",
      "barcode-generate",
      "browser-task",
      "check-domain",
      "convert-format",
      "crypto-fear-greed",
      "crypto-market-cap",
      "crypto-news",
      "crypto-ohlcv",
      "crypto-price",
      "crypto-sentiment",
      "currency-convert",
      "design-create",
      "diff-text",
      "domain-check",
      "email-find",
      "email-send",
      "email-verify",
      "extract-entities",
      "extract-metadata",
      "extract-page",
      "extract-pdf",
      "fact-check",
      "generate-hash",
      "generate-image",
      "generate-uuid",
      "html-to-markdown",
      "image-generate",
      "image-remove-bg",
      "ip-lookup",
      "jsonpath-query",
      "language-detect",
      "news-search",
      "ocr-extract",
      "phone-validate",
      "pii-detect",
      "qr-code",
      "readability-score",
      "regex-generate",
      "research-report",
      "rss-parse",
      "screenshot-capture",
      "search-web",
      "semantic-search",
      "send-email",
      "sentiment-analysis",
      "session-create",
      "session-message",
      "summarize",
      "text-to-speech",
      "timezone-convert",
      "token-lookup",
      "transcribe-audio",
      "transform-text",
      "url-shorten",
      "validate-data",
      "video-generate",
      "web-scrape",
      "web-search",
      "webhook-send",
      "whois-lookup",
      "workflow-agent"
    ],
    "names_truncated": false,
    "sha256": "ffabf2fbaf1b8bd6265e0294e15fae6c4443bbea3a848ef0fa778b967e47cec5"
  },
  "tools_complete": true,
  "tools_observed_at": "2026-11-08T17:27:07.240473+00:00",
  "version": null
}

Pin and review

Keep an accepted snapshot in agents.lock.json. CI returns allow, review or block with reasons.

Gaps default to review. A lock records your acceptance, not a supplier attestation.

API reference

Test an explicit task

Verified domain owners can publish up to five exact-match sandbox fixtures and opt in to a test run. Results include latency, output hashes and regressions.

POST /api/v1/dependencies/task-checks?domain=… while signed in. See the integration guide.

Inspect proof coverage

Domain control, a declared business identifier and a name-matched company record are separate evidence.

Current coverage and measurement date · Verify your domain

Optional SealKeeper evidence

Verify issuer signatures, subject and freshness from the public key document. Task evidence stays separate from Agenstry measurements.

A valid SEAL does not establish domain ownership, legal identity, key possession or execution permission.

Credential verification API · Issuer documentation

Smithery endpoint migration · Agent monitoring · Methodology