product_liability_screen
One-call product-safety + liability read for a MANUFACTURER or brand. Joins three public-record legs: product recalls (CPSC consumer products + openFDA drug/device/food enforcement, keyed by manufacturer), federal-court litigation (CourtListener dockets whose caption actually names the brand), an...
This record as markdown: /tools/io-github-blackboxfoundry-livedatalink/product-liability-screen.md
What product_liability_screen does on Livedatalink
AI agents call product_liability_screen 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 |
|---|---|---|---|
since | string | — | Optional lower-bound date (YYYY-MM-DD) for FDA recalls. |
state | string | — | Optional 2-letter state to scope the CFPB complaint leg (e.g. 'CA'). |
company | string | — | Alias for manufacturer; either may be supplied. |
manufacturer | string | Yes | Manufacturer or brand name to screen (e.g. 'Peloton', 'Fisher-Price'). |
Parameters from the server's own tool schema.
Why product_liability_screen is rated Low
Even though product_liability_screen only reads data, uncontrolled read access leaks sensitive information and racks up API costs: an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.
Attacks that exploit this kind of access
The rule that runs product_liability_screen 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 product_liability_screen, this is the rule to start with:
product_liability_screen 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 product_liability_screen call is checked against it from then on.
Questions about product_liability_screen
One-call product-safety + liability read for a MANUFACTURER or brand. Joins three public-record legs: product recalls (CPSC consumer products + openFDA drug/device/food enforcement, keyed by manufacturer), federal-court litigation (CourtListener dockets whose caption actually names the brand), and CFPB consumer-complaint volume. Returns a rolled-up read (CLEAN / WATCH / ELEVATED LIABILITY SIGNALS) with recall count and severity (FDA Class I / death-related = high), litigation hits (total + last-3-years), and complaint volume, plus an itemized interpretation. A leg that fails is noted, not fatal. NHTSA vehicle recalls need a specific year+make+model so are out of scope here (use recall_screen for a vehicle). Premium cross-source synthesis; informational public-record synthesis, NOT legal advice. It is categorised as a Read tool in the Livedatalink MCP Server, which means it retrieves data without modifying state.
product_liability_screen accepts 4 parameters: since, state, company, manufacturer. Required: manufacturer. 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 product_liability_screen: 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.
product_liability_screen 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 product_liability_screen 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 product_liability_screen. 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.
product_liability_screen 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