You're viewing a demo portfolio

Join the waitlist
PRSM

fda_search_warning_letters

Active

Tool of FDA Data MCP

declared in 0.1.0

Search official FDA warning letters with full-text content from the FDA website. Use keyword search for the actual letter body, or filter by company name, issuing office, subject, MARCS-CMS number, product type, or letter issue date. Adds prospecting filters: status (open|responded|closed, derived from response/closeout dates), letter_category (CGMP-manufacturing | BIMO | listing | OPDP/promotion | 503B/compounding | import — heuristic, derived from issuing_office/subject/product_type), and violation_theme (cgmp_subsystem | data_integrity | validation | bimo | listing | promotion — keyword/FTS-derived over subject+body). Set dedupe=true to collapse near-identical letters sharing a MARCS-CMS case number to one canonical row. Each row exposes derived status and letter_category, plus fei_number for one-hop navigation to fda_citations and fda_inspections. This adds narrative context beyond fda_compliance_actions, which only contains dashboard metadata. NOTE: violation_theme and letter_category are best-effort heuristics over free-text fields; keyword cannot be scoped to a parsed cited-violations sub-section because the corpus only stores subject + full letter body.

Parameters schema

{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "limit": {
      "type": "integer",
      "default": 100,
      "maximum": 500,
      "minimum": 1,
      "description": "Max results to return (1-500)"
    },
    "dedupe": {
      "type": "boolean",
      "default": false,
      "description": "Collapse letters sharing a MARCS-CMS case number to one canonical row (recommended for prospecting)"
    },
    "offset": {
      "type": "integer",
      "default": 0,
      "maximum": 9007199254740991,
      "minimum": 0,
      "description": "Result offset for pagination"
    },
    "status": {
      "enum": [
        "open",
        "responded",
        "closed"
      ],
      "type": "string",
      "description": "Derived status: closed (has closeout date), responded (has response date), or open"
    },
    "date_to": {
      "type": "string",
      "pattern": "^\\d{4}-\\d{2}-\\d{2}$",
      "description": "End date for letter_issue_date range (YYYY-MM-DD)"
    },
    "keyword": {
      "type": "string",
      "maxLength": 500,
      "description": "Full-text query for the warning letter body and subject"
    },
    "subject": {
      "type": "string",
      "maxLength": 500,
      "description": "Subject line text (partial match)"
    },
    "date_from": {
      "type": "string",
      "pattern": "^\\d{4}-\\d{2}-\\d{2}$",
      "description": "Start date for letter_issue_date range (YYYY-MM-DD)"
    },
    "company_name": {
      "type": "string",
      "maxLength": 500,
      "description": "Company name (fuzzy match)"
    },
    "product_type": {
      "type": "string",
      "maxLength": 200,
      "description": "Product type from the letter page (e.g. Drugs, Devices, Food)"
    },
    "issuing_office": {
      "type": "string",
      "maxLength": 500,
      "description": "Issuing office or center name (partial match)"
    },
    "letter_category": {
      "enum": [
        "CGMP-manufacturing",
        "BIMO",
        "listing",
        "OPDP/promotion",
        "503B/compounding",
        "import"
      ],
      "type": "string",
      "description": "Heuristic category derived from issuing_office/subject/product_type"
    },
    "violation_theme": {
      "enum": [
        "cgmp_subsystem",
        "data_integrity",
        "validation",
        "bimo",
        "listing",
        "promotion"
      ],
      "type": "string",
      "description": "Heuristic violation theme derived from subject and letter body text"
    },
    "marcs_cms_number": {
      "type": "string",
      "pattern": "^\\d{3,10}$",
      "description": "MARCS-CMS case number shown on the letter page"
    }
  }
}

What this tool wraps· 0 endpoints

min confidence0.700.50

No endpoints wrapped at confidence ≥ 0.50.

Parent server

FDA Data MCP

https://github.com/medley/fda-data

1/7 registries
View full server →