Search stored information by pattern. Searches both keys and values.
AI agents call search_data to retrieve information from Store MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The search_data tool retrieves and queries stored information without side effects. It does not create, modify, delete, or execute operations. It falls squarely within the Read category as a retrieval operation. Severity is low because even if misused, searching data poses minimal risk—it cannot alter state, move funds, or execute external code.
From the tool's definition Tool description states "Search stored information by pattern. Searches both keys and values." The action is searching/querying existing data without modification, creation, or deletion. This is a read-only operation.
Attacks that exploit this kind of access
Search stored information by pattern. Searches both keys and values. It is categorised as a Read tool in the Store MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Store MCP Server MCP server in PolicyLayer and add a rule for search_data: 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 Store MCP Server. Nothing to install.
search_data 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_data 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_data. 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_data is provided by the Store MCP Server MCP server (mariano-cecowski/store_mcp). 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 →