{
  "schema": "varexis-public-evidence-record/0.3",
  "generated_at_utc": "2026-10-22T23:52:06.542Z",
  "record_id": "VXI-EXT-PROCUREMENT-MCP-ELICITATION-FORM-SENSITIVE-INPUT-BOUNDARY-01-v1",
  "record_kind": "external_reference",
  "title": "MCP elicitation: Credentials belong outside form responses",
  "system": "Model Context Protocol",
  "evidence_family": "vendor_evidence_review",
  "index_status": "PUBLIC_SAFE_SOURCE_REVIEW",
  "evidence_state": "PRIMARY_DOCUMENTATION_REVIEW_ONLY",
  "canonical_question": "May an MCP server collect API keys or payment credentials through form elicitation?",
  "near_questions": [
    "Which MCP elicitation mode can request sensitive credentials?",
    "Should an agent return an API key in an MCP form response?",
    "Does MCP URL elicitation replace client-to-server authorization?",
    "Are contact details and access tokens treated the same in MCP forms?"
  ],
  "supported_claims": [
    {
      "claim": "MCP 2026-07-28 prohibits requesting passwords, API keys, access tokens or payment credentials through form elicitation and requires URL mode for those interactions. General contact information is not categorically prohibited. URL elicitation is separate from authorizing the MCP client's access to the server.",
      "reliance": "DOCUMENTED_CAPABILITY_ONLY"
    }
  ],
  "not_demonstrated_claims": [
    "Proof that a hosted page is trustworthy, a deployment follows the specification or credentials were never logged",
    "A blanket ban on all personal information in forms or automatic permission to open an external URL",
    "Buyer deployment testing, live runtime enforcement, certification or permission to act",
    "Expanded capabilities or licences for existing INDEX executables"
  ],
  "public_summary": "MCP 2026-07-28 prohibits requesting passwords, API keys, access tokens or payment credentials through form elicitation and requires URL mode for those interactions. General contact information is not categorically prohibited. URL elicitation is separate from authorizing the MCP client's access to the server.",
  "related_record_ids": [],
  "source_review": {
    "source_type": "official_external_documentation",
    "source_title": "MCP elicitation",
    "source_url": "https://modelcontextprotocol.io/specification/2026-07-28/client/elicitation",
    "checked_on": "2026-10-22",
    "candidate_record_id": "VXI-EXT-PROCUREMENT-MCP-ELICITATION-FORM-SENSITIVE-INPUT-BOUNDARY-01-v1",
    "candidate_record_sha256": "1f47c4f475919090668ed092ff233767dc52b54cc91b1c80daa6bcab4cae1026",
    "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": "MCP 2026-07-28 prohibits requesting passwords, API keys, access tokens or payment credentials through form elicitation and requires URL mode for those interactions. General contact information is not categorically prohibited. URL elicitation is separate from authorizing the MCP client's access to the server.",
    "required_buyer_context": "Negotiated MCP version, elicitation mode and requested fields; Requesting server and external URL identity with user consent; Credential routing, logging boundaries and client-to-server authorization. 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": "May an MCP server collect API keys or payment credentials through form elicitation?",
    "documented_statement": {
      "status": "documented",
      "statement": "MCP 2026-07-28 prohibits requesting passwords, API keys, access tokens or payment credentials through form elicitation and requires URL mode for those interactions. General contact information is not categorically prohibited. URL elicitation is separate from authorizing the MCP client's access to the server.",
      "source_ids": [
        "mcp-elicitation"
      ]
    },
    "review_inference": {
      "status": "review_inference",
      "statement": "A declaration review should classify requested fields and identify where secrets travel.",
      "source_ids": [
        "mcp-elicitation"
      ]
    },
    "buyer_evidence_required": [
      "Negotiated MCP version, elicitation mode and requested fields",
      "Requesting server and external URL identity with user consent",
      "Credential routing, logging boundaries and client-to-server authorization"
    ],
    "review_condition": {
      "status": "varexis_review_policy",
      "statement": "Refuse reliance on a credential-safe flow when secrets are requested through form elicitation or the external recipient is unverified."
    },
    "unknowns": "The buyer host behavior, recipient trust, credential storage and logging are unobserved.",
    "unknown_finding": {
      "status": "unknown",
      "statement": "The buyer host behavior, recipient trust, credential storage and logging are unobserved."
    },
    "evidence_sources": [
      {
        "source_id": "mcp-elicitation",
        "url": "https://modelcontextprotocol.io/specification/2026-07-28/client/elicitation",
        "final_url": "https://modelcontextprotocol.io/specification/2026-07-28/client/elicitation",
        "title": "MCP elicitation",
        "checked_on": "2026-10-22",
        "captured_at_utc": "2026-10-22T23:48:43.258Z",
        "version_context": "MCP specification 2026-07-28; URL completion and sensitive-input boundaries.",
        "sha256": "2c0ded61a1373af5cd8db16b1300c4a2de1a5e20b5f3faf6f023a25832198ae7",
        "bytes": 713929,
        "hash_basis": "Decoded HTTP response body bytes; identifies captured content, not truth or certification",
        "reviewed_sections": [
          "URL mode",
          "Response actions",
          "Sensitive information"
        ],
        "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": "Recognize an inappropriate credential-collection path before delegating access to a tool.",
      "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": "Recognize an inappropriate credential-collection path before delegating access to a tool.",
    "refusal_conditions": [
      "Refuse reliance on a credential-safe flow when secrets are requested through form elicitation or the external recipient is unverified."
    ]
  },
  "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": "Recognize an inappropriate credential-collection path before delegating access to a tool.",
    "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#mcp-elicitation-form-sensitive-input-boundary",
  "machine_readable_record": "/varexis-index/records/mcp-elicitation-form-sensitive-input-boundary.json"
}
