AI agents call search_by_study_uid to retrieve information from AWS without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool performs a query/lookup by study identifier. Despite empty description, the name strongly indicates a retrieval operation with no mutation. Classified as Read with medium-high confidence given the lack of descriptive details. Severity is low because search operations typically have minimal blast radius.
From the tool's definition Tool name 'search_by_study_uid' contains 'search', which is a classic Read operation pattern. No description provided to suggest side effects.
Documented attack patterns abuse exactly the kind of access search_by_study_uid gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and AWS, and nothing reaches the server without passing your rules. This is the rule we recommend for search_by_study_uid:
{
"version": "1",
"default": "deny",
"tools": {
"search_by_study_uid": {}
}
} search_by_study_uid is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
search_by_study_uid. It is categorised as a Read tool in the AWS MCP Server, which means it retrieves data without modifying state.
Register the AWS MCP server in PolicyLayer and add a rule for search_by_study_uid: 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 AWS. Nothing to install.
search_by_study_uid 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 search_by_study_uid 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 search_by_study_uid. 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.
search_by_study_uid is provided by the AWS MCP server (@awslabs/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from AWS, 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.
300 AWS tools catalogued and risk-classified — across an index of 43,000+ MCP servers.