search_tools
AI agents call search_tools to retrieve information from Mdb Mcp Gateway without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool appears to search a catalog of available tools/services via the MCP gateway. This is a read operation that retrieves metadata about tools without modifying or executing them. No side effects, no data modification, no code execution. The empty description reduces confidence slightly, but context from server purpose and sibling tools strongly suggests a search/discovery function typical of read operations.
From the tool's definition Tool name 'search_tools' with 'search' verb indicates retrieval/query operation. Server description emphasizes 'retrieval infrastructure' and 'hybrid search on MongoDB Atlas' for routing queries.
Attacks that exploit this kind of access
search_tools. It is categorised as a Read tool in the Mdb Mcp Gateway MCP Server, which means it retrieves data without modifying state.
Register the Mdb Mcp Gateway MCP server in PolicyLayer and add a rule for search_tools: 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 Mdb Mcp Gateway. Nothing to install.
search_tools 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_tools 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_tools. 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_tools is provided by the Mdb Mcp Gateway MCP server (ranfysvalle02/m-gate). 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 →