Low Risk

fda.recalls

FDA drug recalls (Recall Enterprise System). Class I = could cause death/serious harm (material adverse event); Class II/III lower. Filter by recalling firm, drug, classification, and recency; returns classification, reason, status, dates, and the recalling firm's resolved ticker (null if private...

Part of the Arkolith server.

fda.recalls is read-only, but an agent in a loop can still rack up calls and cost. PolicyLayer caps every call before it runs. Live in minutes.

SECURE ARKOLITH →

Free to start. No card required.

AI agents call fda.recalls to retrieve information from Arkolith without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.

Even though fda.recalls only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.

Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "fda.recalls": {}
  }
}

See the full Arkolith policy for all 32 tools.

Get this rule live on your own Arkolith server in minutes. PolicyLayer enforces it on every call, before it runs.

ENFORCE ON MY ARKOLITH →

View all 32 tools →

These attack patterns abuse exactly the kind of access fda.recalls gives an agent. Each links to the full case and the policy that stops it:

Browse the full MCP Attack Database →

Every attack above starts with a tool call. PolicyLayer checks each one against your policy first, so fda.recalls only ever does what you allow.

SECURE ARKOLITH →

Other read tools across the catalogue. The same approach applies to each: allow, with a rate cap to control cost.

What does the fda.recalls tool do? +

FDA drug recalls (Recall Enterprise System). Class I = could cause death/serious harm (material adverse event); Class II/III lower. Filter by recalling firm, drug, classification, and recency; returns classification, reason, status, dates, and the recalling firm's resolved ticker (null if private). CAVEAT: enforcement data updates only WEEKLY and FDA does not revise recall status after classification — can be stale/frozen; not for real-time alerting. Public-domain openFDA.. It is categorised as a Read tool in the Arkolith MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on fda.recalls? +

Register the Arkolith MCP server in PolicyLayer and add a rule for fda.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 Arkolith. Nothing to install.

What risk level is fda.recalls? +

fda.recalls is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit fda.recalls? +

Yes. Add a rate_limit block to the fda.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.

How do I block fda.recalls completely? +

Set action: deny in the PolicyLayer policy for fda.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.

What MCP server provides fda.recalls? +

fda.recalls is provided by the Arkolith MCP server (https://arkolith.com/api/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Arkolith tool call.

Deterministic rules across all 32 Arkolith 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.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.