openfda_adverse_searcher
AI agents call openfda_adverse_searcher to retrieve information from CzechMedMCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool appears designed to search and retrieve adverse event information from the OpenFDA database, consistent with query operations that do not modify, execute code, or cause destructive changes. However, confidence is moderate (0.7) because the description is empty; if this tool performed unexpected operations (e.g., triggering automated reports or modifying registries), it could be reclassified.
From the tool's definition Tool name 'openfda_adverse_searcher' indicates searching/querying adverse event data. 'Searcher' suffix and positioning within a biomedical database context suggests data retrieval with no side effects.
Attacks that exploit this kind of access
openfda_adverse_searcher. It is categorised as a Read tool in the CzechMedMCP MCP Server, which means it retrieves data without modifying state.
Register the CzechMed MCP server in PolicyLayer and add a rule for openfda_adverse_searcher: 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 CzechMedMCP. Nothing to install.
openfda_adverse_searcher 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 openfda_adverse_searcher 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 openfda_adverse_searcher. 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.
openfda_adverse_searcher is provided by the CzechMed MCP server (petrsovadina/czechmedmcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →