Comprehensive company profile: facilities (with addresses and operations), enforcement actions (recalls), 510(k) clearances, PMA approvals, and drug applications for a single company and its known aliases. Costs 5 credits. Excludes: inspection history, citations, compliance actions (warning lette...
Risk signalsHigh parameter count (11 properties)
Part of the FDA Data MCP server.
Free to start. No card required.
AI agents use fda_company_full to create or modify resources in FDA Data MCP. Write operations carry medium risk because an autonomous agent could trigger bulk unintended modifications. Rate limits prevent a single agent session from making hundreds of changes in rapid succession. Argument validation ensures the agent passes expected values.
Without a policy, an AI agent could call fda_company_full repeatedly, creating or modifying resources faster than any human could review. PolicyLayer's rate limiting ensures write operations happen at a controlled pace, and argument validation catches malformed or unexpected inputs before they reach FDA Data MCP.
Write tools can modify data. A rate limit prevents runaway bulk operations from AI agents.
{
"version": "1",
"default": "deny",
"tools": {
"fda_company_full": {
"limits": [
{
"counter": "fda_company_full_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}See the full FDA Data MCP policy for all 48 tools.
These attack patterns abuse exactly the kind of access fda_company_full gives an agent. Each links to the full case and the policy that stops it:
Other write tools across the catalogue. The same approach applies to each: rate-limit and validate the arguments.
Comprehensive company profile: facilities (with addresses and operations), enforcement actions (recalls), 510(k) clearances, PMA approvals, and drug applications for a single company and its known aliases. Costs 5 credits. Excludes: inspection history, citations, compliance actions (warning letters), facility-level product lists, import refusals, and family rollups across separate child company records. For family rollups: call fda_suggest_subsidiaries first, then use fda_save_aliases for true same-company names or fda_link_subsidiaries for distinct child companies. Related: fda_suggest_subsidiaries (discover subsidiaries), fda_link_subsidiaries (create explicit family links), fda_get_facility (per-facility products, operations type, risk summary by FEI), fda_inspections (inspection history by FEI or company), fda_citations (CFR violations by FEI), fda_compliance_actions (warning letters/seizures by FEI or company), fda_search_aphis (animal health facilities for vet companies), fda_drug_shortages (active drug shortages).. It is categorised as a Write tool in the FDA Data MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the FDA Data MCP server in PolicyLayer and add a rule for fda_company_full: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches FDA Data MCP. Nothing to install.
fda_company_full is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the fda_company_full rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for fda_company_full. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
fda_company_full is provided by the FDA Data MCP server (https://www.regdatalab.com/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 48 FDA Data MCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4,600+ MCP servers and 31,000+ tools scanned and risk-classified.