{
  "schema": "varexis-public-evidence-record/0.3",
  "generated_at_utc": "2026-10-22T23:52:06.542Z",
  "record_id": "VXI-EXT-PROCUREMENT-AGENTCORE-POLICY-MCP-METHOD-COVERAGE-BOUNDARY-01-v1",
  "record_kind": "external_reference",
  "title": "AgentCore Gateway Policy: Tool checks exclude prompts and resources",
  "system": "Amazon Web Services",
  "evidence_family": "vendor_evidence_review",
  "index_status": "PUBLIC_SAFE_SOURCE_REVIEW",
  "evidence_state": "PRIMARY_DOCUMENTATION_REVIEW_ONLY",
  "canonical_question": "Does AgentCore Gateway Policy apply its tool rules to MCP prompts and resources?",
  "near_questions": [
    "Are MCP resources covered by AgentCore tool policies?",
    "Does AgentCore ENFORCE mode also evaluate prompts/get?",
    "Which MCP methods fall outside AgentCore Gateway Policy?",
    "Can a tool-only AgentCore policy establish all-method access control?"
  ],
  "supported_claims": [
    {
      "claim": "AgentCore documents Policy evaluation for MCP tools only. Its Policy layer allows the listed prompt and resource methods regardless of evaluation mode. Gateway authentication and other access controls remain separate. A tool-policy configuration therefore does not establish equivalent policy coverage for prompts or resources.",
      "reliance": "DOCUMENTED_CAPABILITY_ONLY"
    }
  ],
  "not_demonstrated_claims": [
    "Unauthenticated public access, absence of other controls or a proven bypass in a buyer deployment",
    "INDEX enforcement or validation of a deployed gateway",
    "Buyer deployment testing, live runtime enforcement, certification or permission to act",
    "Expanded capabilities or licences for existing INDEX executables"
  ],
  "public_summary": "AgentCore documents Policy evaluation for MCP tools only. Its Policy layer allows the listed prompt and resource methods regardless of evaluation mode. Gateway authentication and other access controls remain separate. A tool-policy configuration therefore does not establish equivalent policy coverage for prompts or resources.",
  "related_record_ids": [],
  "source_review": {
    "source_type": "official_external_documentation",
    "source_title": "Use an AgentCore Gateway with Policy in AgentCore",
    "source_url": "https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/use-gateway-with-policy.html",
    "checked_on": "2026-10-22",
    "candidate_record_id": "VXI-EXT-PROCUREMENT-AGENTCORE-POLICY-MCP-METHOD-COVERAGE-BOUNDARY-01-v1",
    "candidate_record_sha256": "a09b37690d5f31d8bc54af922df9ff12f75a245731afb0bd43953cfea335a2a3",
    "method": "Primary documentation reviewed for the published bounded statement.",
    "deployment_tested_by_varexis": false,
    "revalidation": "The delivered snapshot preserves the review date shown. Recheck current primary documentation and deployment context before relying on present applicability; payment does not trigger fresh research."
  },
  "answer_policy": {
    "classification": "DOCUMENTED_WITH_DEPLOYMENT_BOUNDARY",
    "bounded_answer": "AgentCore documents Policy evaluation for MCP tools only. Its Policy layer allows the listed prompt and resource methods regardless of evaluation mode. Gateway authentication and other access controls remain separate. A tool-policy configuration therefore does not establish equivalent policy coverage for prompts or resources.",
    "required_buyer_context": "Gateway identity, configured Policy mode and engine binding; MCP methods exposed by each target; Authentication and separate controls for prompts and resources. Buyer deployment not inspected.",
    "missing_evidence": "A broader claim needs evidence matching the intended use. Payment does not upgrade the evidence state."
  },
  "private_boundary": "Raw logs, thresholds, private paths, source code, protected mechanisms and reconstruction-level details are excluded from public and paid delivery.",
  "decision_profile": {
    "schema": "varexis-vendor-evidence-review/1",
    "review_status": "documentation_review_only",
    "checked_on": "2026-10-22",
    "claim_to_check": "Does AgentCore Gateway Policy apply its tool rules to MCP prompts and resources?",
    "documented_statement": {
      "status": "documented",
      "statement": "AgentCore documents Policy evaluation for MCP tools only. Its Policy layer allows the listed prompt and resource methods regardless of evaluation mode. Gateway authentication and other access controls remain separate. A tool-policy configuration therefore does not establish equivalent policy coverage for prompts or resources.",
      "source_ids": [
        "agentcore-policy"
      ]
    },
    "review_inference": {
      "status": "review_inference",
      "statement": "The review should enumerate protected methods and controls outside the tool-policy layer.",
      "source_ids": [
        "agentcore-policy"
      ]
    },
    "buyer_evidence_required": [
      "Gateway identity, configured Policy mode and engine binding",
      "MCP methods exposed by each target",
      "Authentication and separate controls for prompts and resources"
    ],
    "review_condition": {
      "status": "varexis_review_policy",
      "statement": "Refuse a claim that tool policies govern every MCP method without method-specific evidence."
    },
    "unknowns": "The buyer exposed methods, other control layers and effective request decisions are unobserved.",
    "unknown_finding": {
      "status": "unknown",
      "statement": "The buyer exposed methods, other control layers and effective request decisions are unobserved."
    },
    "evidence_sources": [
      {
        "source_id": "agentcore-policy",
        "url": "https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/use-gateway-with-policy.html",
        "final_url": "https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/use-gateway-with-policy.html",
        "title": "Use an AgentCore Gateway with Policy in AgentCore",
        "checked_on": "2026-10-22",
        "captured_at_utc": "2026-10-22T23:48:43.305Z",
        "version_context": "Rolling AgentCore Gateway developer guide; scope of Policy evaluation, not a buyer deployment test.",
        "sha256": "a28097d77e698680974be0a916d14ef16eedad6dd52c2799ccace47c803f743f",
        "bytes": 22175,
        "hash_basis": "Decoded HTTP response body bytes; identifies captured content, not truth or certification",
        "reviewed_sections": [
          "MCP tools only",
          "List AgentCore Gateway Tools with Policy"
        ],
        "capture_status": 200,
        "rights_review": "Factual paraphrase and source metadata only; response body retained privately and not redistributed."
      }
    ],
    "observed_deployment": false,
    "commercial_reliance_boundary": "Documentation review only; the buyer must establish applicability and actual outcomes. INDEX does not inspect or control the deployment.",
    "paid_value": {
      "decision_context": "Expose method-level gaps before relying on an agent gateway's permission declaration.",
      "free": "Complete review, sources, practical questions and limitations; may be saved locally.",
      "single_request": "Existing server-saved version-bound route snapshot for later authenticated retrieval.",
      "evidence_receipt": "The same snapshot plus the existing unsigned delivery receipt.",
      "excluded": [
        "Fresh vendor research",
        "Continuous monitoring or change alerts",
        "Testing the buyer configuration",
        "Private evidence or vendor certification"
      ],
      "integrity": "Hashes identify content versions; they do not prove truth or provide a signature."
    },
    "revalidation": {
      "trigger": "A saved purchase does not recheck the source or buyer configuration.",
      "specific_watch": "Recheck the documented behavior, product version and buyer evidence before relying on a current outcome."
    },
    "buyer_relevance": "Expose method-level gaps before relying on an agent gateway's permission declaration.",
    "refusal_conditions": [
      "Refuse a claim that tool policies govern every MCP method without method-specific evidence."
    ]
  },
  "niche": {
    "niche_id": "agent-authority-action-evidence",
    "label": "Agent Authority & Action Evidence",
    "classification_id": "governance",
    "classification_label": "Agent Governance & Policy Boundaries",
    "topic_id": "governance",
    "buyer_intent": "Expose method-level gaps before relying on an agent gateway's permission declaration.",
    "comparison_role": "supplementary_discovery"
  },
  "paid_access_note": "The full published answer and boundaries are free. Paid access saves the selected route and source versions, with an unsigned receipt when purchased. Preview coverage before paying. Fresh research, bespoke assessment and protected evidence are excluded.",
  "service_route": {
    "request_guide": "/varexis-index/request.html",
    "request_workflow": "/varexis-index/request-workflow.json",
    "service_id": "single_request",
    "service_routes_url": "/varexis-index/service-routes.json",
    "payment_required": true,
    "availability_endpoint": "/api/index/capabilities",
    "operational_status": "AUTOMATIC_SERVICE_CAPABILITIES_GATED",
    "checkout_url": "/index-access"
  },
  "authority_boundary": "VAREXIS-INDEX informs evidence reliance. It does not provide advice, certification, deployment authority, security assurance, production approval, or guarantee.",
  "human_page": "/varexis-index/catalog.html#agentcore-policy-mcp-method-coverage-boundary",
  "machine_readable_record": "/varexis-index/records/agentcore-policy-mcp-method-coverage-boundary.json"
}
