Evidence row 1747595

What was observed

{
  "count": 2,
  "tools": [
    {
      "description": "\n    Get information about available recall data sources.\n    \n    Returns a list of all supported regulatory agencies and their coverage.\n    This is a free call that does not consume API credits.\n    \n    Returns:\n        Dictionary with data sources and their descriptions\n    ",
      "inputSchema": {
        "properties": {},
        "title": "get_data_sourcesArguments",
        "type": "object"
      },
      "name": "get_data_sources"
    },
    {
      "description": "\n    Search for recalled products similar to your query.\n    \n    This tool searches DeepRecall's global product safety database using AI-powered\n    multimodal matching. Provide a text description and/or product images to find\n    similar recalled products.\n    \n    Use Cases:\n    - Pre-purchase safety checks: Before buying, verify if similar products were recalled\n    - Supplier vetting: Check if a supplier's products have safety issues\n    - Marketplace compliance: Verify products against recall databases\n    - Consumer protection: Identify potentially hazardous products\n    \n    Data Sources:\n    - us_cpsc: US Consumer Product Safety Commission\n    - us_fda: US Food and Drug Administration\n    - safety_gate: EU Safety Gate (Europe)\n    - uk_opss: UK Office for Product Safety & Standards\n    - canada_recalls: Health Canada Recalls\n    - oecd: OECD GlobalRecalls portal\n    - rappel_conso: French Consumer Recalls\n    - accc_recalls: Australian Competition and Consumer Commission\n    \n    Cost: 1 API credit per search\n    \n    Args:\n        content_description: Text description of the product (e.g., \"children's toy with small parts\")\n        image_urls: List of product image URLs for visual matching (1-10 images)\n        filter_by_data_sources: Limit search to specific agencies (optional)\n        top_k: Number of results (1-100, default: 10)\n        model_name: Fusion model - fuse_max (recommended), fuse_flex, or fuse\n        input_weights: Weights for [text, images], must sum to 1.0\n        api_key: Your DeepRecall API key (optional if provided via X-API-Key header)\n    \n    Returns:\n        Search results with matched recalls, scores, and product details\n    \n    Example:\n        search_recalls(\n            content_description=\"baby crib with drop-side rails\",\n            top_k=5\n        )\n    ",
      "inputSchema": {
        "properties": {
          "api_key": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "title": "Api Key"
          },
          "content_description": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "title": "Content Description"
          },
          "filter_by_data_sources": {
            "anyOf": [
              {
                "items": {
                  "type": "string"
                },
                "type": "array"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "title": "Filter By Data Sources"
          },
          "image_urls": {
            "anyOf": [
              {
                "items": {
                  "type": "string"
                },
                "type": "array"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "title": "Image Urls"
          },
          "input_weights": {
            "default": [
              0.5,
              0.5
            ],
            "items": {
              "type": "number"
            },
            "title": "Input Weights",
            "type": "array"
          },
          "model_name": {
            "default": "fuse_max",
            "title": "Model Name",
            "type": "string"
          },
          "top_k": {
            "default": 10,
            "title": "Top K",
            "type": "integer"
          }
        },
        "title": "search_recallsArguments",
        "type": "object"
      },
      "name": "search_recalls"
    }
  ]
}

What the leaf hashes

{"body":"b54ecea111a63bf4c2a7e39197af84ad6cdc23e2e98b12f119904d10504c5efd","id":1747595,"kind":"mcp.tools","method":"probe.mcp/1","observed_us":1793516638937835,"prev":null,"subject":"544063d0-bc0d-4b78-8be3-671efd3bccd4","subject_kind":"endpoint"}

Proof

Its day has not closed yet. A day closes ten minutes after midnight UTC; the proof appears here then.