Experimental database search (limited functionality)
AI agents call experimental_search to retrieve information from Bear MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or queries data from the Bear database without side effects. Although marked 'experimental' and 'limited functionality', search operations are inherently non-destructive reads.
From the tool's definition Tool name is 'experimental_search' and description states it performs 'database search (limited functionality)', with no mention of data modification, deletion, or execution of arbitrary operations.
Attacks that exploit this kind of access
Experimental database search (limited functionality). It is categorised as a Read tool in the Bear MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Bear MCP Server MCP server in PolicyLayer and add a rule for experimental_search: 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 Bear MCP Server. Nothing to install.
experimental_search 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 experimental_search 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 experimental_search. 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.
experimental_search is provided by the Bear MCP Server MCP server (philgetzen/bear-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 →