{
  "schema": "varexis-public-evidence-record/0.3",
  "generated_at_utc": "2026-10-22T21:15:08.873Z",
  "record_id": "VXI-EXT-PROCUREMENT-OPENAI-RESPONSES-MCP-IMPORT-APPROVAL-BOUNDARY-01-v1",
  "record_kind": "external_reference",
  "title": "OpenAI Responses MCP: Imported tools and sharing approval",
  "system": "OpenAI",
  "evidence_family": "vendor_evidence_review",
  "index_status": "PUBLIC_SAFE_SOURCE_REVIEW",
  "evidence_state": "PRIMARY_DOCUMENTATION_REVIEW_ONLY",
  "canonical_question": "Does allowing a remote MCP tool in OpenAI Responses also approve sending it data?",
  "near_questions": [
    "How do allowed_tools and require_approval differ in OpenAI Responses?",
    "Does importing an MCP tool approve its arguments for sharing?",
    "What should be checked before approving an OpenAI remote MCP call?",
    "Does require_approval never grant additional upstream permissions?"
  ],
  "supported_claims": [
    {
      "claim": "OpenAI Responses uses allowed_tools to limit imported MCP tools and a separate require_approval setting for tool-call approval. By default it requests approval before sharing data with a connector or remote MCP server. An approval request exposes the tool and arguments for review; disabling approvals changes that sharing gate, not the remote service permissions.",
      "reliance": "DOCUMENTED_CAPABILITY_ONLY"
    }
  ],
  "not_demonstrated_claims": [
    "Remote permission enforcement, safe arguments or server trust from an allowlist",
    "Buyer deployment testing, live runtime enforcement, certification or permission to act",
    "Expanded capabilities or licences for existing INDEX executables"
  ],
  "public_summary": "OpenAI Responses uses allowed_tools to limit imported MCP tools and a separate require_approval setting for tool-call approval. By default it requests approval before sharing data with a connector or remote MCP server. An approval request exposes the tool and arguments for review; disabling approvals changes that sharing gate, not the remote service permissions.",
  "related_record_ids": [],
  "source_review": {
    "source_type": "official_external_documentation",
    "source_title": "MCP servers",
    "source_url": "https://developers.openai.com/api/docs/guides/tools-connectors-mcp",
    "checked_on": "2026-10-22",
    "candidate_record_id": "VXI-EXT-PROCUREMENT-OPENAI-RESPONSES-MCP-IMPORT-APPROVAL-BOUNDARY-01-v1",
    "candidate_record_sha256": "fd5e4946c283a44647f78a400b83f163091f0aae6e9f914b5db1037a48433dde",
    "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": "OpenAI Responses uses allowed_tools to limit imported MCP tools and a separate require_approval setting for tool-call approval. By default it requests approval before sharing data with a connector or remote MCP server. An approval request exposes the tool and arguments for review; disabling approvals changes that sharing gate, not the remote service permissions.",
    "required_buyer_context": "Responses MCP configuration and server identity; Requested tool arguments and approval response; Remote credential scope and permitted data recipients. 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 allowing a remote MCP tool in OpenAI Responses also approve sending it data?",
    "documented_statement": {
      "status": "documented",
      "statement": "OpenAI Responses uses allowed_tools to limit imported MCP tools and a separate require_approval setting for tool-call approval. By default it requests approval before sharing data with a connector or remote MCP server. An approval request exposes the tool and arguments for review; disabling approvals changes that sharing gate, not the remote service permissions.",
      "source_ids": [
        "openai-mcp"
      ]
    },
    "review_inference": {
      "status": "review_inference",
      "statement": "Tool selection, data-sharing consent and upstream authority require separate evidence.",
      "source_ids": [
        "openai-mcp"
      ]
    },
    "buyer_evidence_required": [
      "Responses MCP configuration and server identity",
      "Requested tool arguments and approval response",
      "Remote credential scope and permitted data recipients"
    ],
    "review_condition": {
      "status": "varexis_review_policy",
      "statement": "Refuse an approved-sharing finding without the applicable approval policy and call-specific authority."
    },
    "unknowns": "Remote server behavior, actual data handling and effective permissions are unobserved.",
    "unknown_finding": {
      "status": "unknown",
      "statement": "Remote server behavior, actual data handling and effective permissions are unobserved."
    },
    "evidence_sources": [
      {
        "source_id": "openai-mcp",
        "url": "https://developers.openai.com/api/docs/guides/tools-connectors-mcp",
        "final_url": "https://developers.openai.com/api/docs/guides/tools-connectors-mcp",
        "title": "MCP servers",
        "checked_on": "2026-10-22",
        "captured_at_utc": "2026-10-22T21:06:14.793Z",
        "version_context": "Rolling official documentation captured on review date; not a pinned software release.",
        "sha256": "f21ef658718e87c7ae3b822db6dc22865a32bc757ce98fcf78a9c1e86c993ab8",
        "bytes": 800602,
        "hash_basis": "Decoded HTTP response body bytes; identifies captured content, not truth or certification",
        "reviewed_sections": [
          "Approval",
          "allowed_tools"
        ],
        "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": "Review agent data egress before permitting a remote tool call.",
      "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": "Review agent data egress before permitting a remote tool call.",
    "refusal_conditions": [
      "Refuse an approved-sharing finding without the applicable approval policy and call-specific authority."
    ]
  },
  "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": "Review agent data egress before permitting a remote tool call.",
    "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#openai-responses-mcp-import-approval-boundary",
  "machine_readable_record": "/varexis-index/records/openai-responses-mcp-import-approval-boundary.json"
}
