Low Risk

search_drug_power_query

Advanced query tool providing direct access to ALL drug API endpoints:

How to control search_drug_power_query ↓

What search_drug_power_query does on OpenFDA FastMCP Server

AI agents call search_drug_power_query to retrieve information from OpenFDA FastMCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

Low Risk

Why search_drug_power_query needs a policy

This tool retrieves and queries public health data without modifying, deleting, or executing arbitrary code. It is fundamentally a Read operation. Severity is medium rather than low because (1) the 'power_query' designation and 'ALL endpoints' access suggests broad data access that could expose sensitive medical information at scale, and (2) unrestricted querying of comprehensive drug adverse event data could enable…

From the tool's definition Tool name contains 'search' and description states 'direct access to ALL drug API endpoints' for querying FDA data. No creation, modification, deletion, execution, or financial operations described.

Documented attack patterns abuse exactly the kind of access search_drug_power_query gives an agent:

How to control search_drug_power_query

PolicyLayer is an MCP gateway — it sits between your AI agents and OpenFDA FastMCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for search_drug_power_query:

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

search_drug_power_query is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.

  1. Create a free account and register OpenFDA FastMCP Server — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
CAP THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about search_drug_power_query

What does the search_drug_power_query tool do? +

Advanced query tool providing direct access to ALL drug API endpoints:. It is categorised as a Read tool in the OpenFDA FastMCP Server MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on search_drug_power_query? +

Register the OpenFDA FastMCP Server MCP server in PolicyLayer and add a rule for search_drug_power_query: 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 OpenFDA FastMCP Server. Nothing to install.

What risk level is search_drug_power_query? +

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

Can I rate-limit search_drug_power_query? +

Yes. Add a rate_limit block to the search_drug_power_query 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 search_drug_power_query completely? +

Set action: deny in the PolicyLayer policy for search_drug_power_query. 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 search_drug_power_query? +

search_drug_power_query is provided by the OpenFDA FastMCP Server MCP server (suyashekhande/openfda-semantic-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every OpenFDA FastMCP Server tool call.

Start from OpenFDA FastMCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

Free to start. No card required.

12 OpenFDA FastMCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// GET IN TOUCH

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

Message sent.

We'll get back to you soon.