fda_food_recalls
FDA food enforcement actions (food recalls). Filter by product description, recall classification, state, or date range. Used for retail food safety monitoring, supply chain compliance, restaurant management.
This record as markdown: /tools/io-github-blackboxfoundry-livedatalink/fda-food-recalls.md
What fda_food_recalls does on Livedatalink
AI agents call fda_food_recalls to retrieve information from Livedatalink without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
limit | number | — | Maximum rows to return (default 25, max 100). |
query | string | — | Optional product description search term. |
state | string | — | Optional 2-letter state filter. |
end_date | string | — | Inclusive ISO date upper bound (YYYY-MM-DD). |
start_date | string | — | Inclusive ISO date lower bound (YYYY-MM-DD). |
classification | string | — | Recall severity: I (most severe), II, III. |
Parameters from the server's own tool schema.
Why fda_food_recalls is rated Low
This tool retrieves and filters existing FDA food recall data. It is a read-only query operation that returns information for compliance and safety monitoring purposes. There are no side effects, data modifications, code execution, or financial implications. The worst-case misuse (an agent requesting irrelevant or excessive recalls data) poses minimal risk.
From the tool's definition Tool description indicates it 'Filter[s] by product description, recall classification, state, or date range' and is 'Used for retail food safety monitoring, supply chain compliance, restaurant management.' These are all query/retrieval operations with no…
Attacks that exploit this kind of access
The rule that runs fda_food_recalls safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Livedatalink, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For fda_food_recalls, this is the rule to start with:
fda_food_recalls is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Livedatalink, apply this rule, and every fda_food_recalls call is checked against it from then on.
Questions about fda_food_recalls
FDA food enforcement actions (food recalls). Filter by product description, recall classification, state, or date range. Used for retail food safety monitoring, supply chain compliance, restaurant management. It is categorised as a Read tool in the Livedatalink MCP Server, which means it retrieves data without modifying state.
fda_food_recalls accepts 6 parameters: limit, query, state, end_date, start_date, classification. The full parameter table on this page comes from the server's own tool schema.
Register the Livedatalink MCP server in PolicyLayer and add a rule for fda_food_recalls: 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 Livedatalink. Nothing to install.
fda_food_recalls is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the fda_food_recalls 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_food_recalls. 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_food_recalls is provided by the Livedatalink MCP server (https://livedatalink.ai/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Livedatalink, and thousands of servers like it.
This server
Across the catalogue