Search Tools by Keyword.
AI agents call search_mcp_tools to retrieve information from Nest Protect MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a read-only search operation to discover or list MCP tools matching keyword criteria. It has no side effects, does not execute commands, and does not modify or delete data. The blast radius of misuse is minimal—an attacker could enumerate available tools but cannot directly harm devices, data, or systems. Classified as Read with low severity.
From the tool's definition Tool name 'search_mcp_tools' and description 'Search Tools by Keyword' indicate a query/search operation that retrieves information without modifying state.
Attacks that exploit this kind of access
Search Tools by Keyword. It is categorised as a Read tool in the Nest Protect MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Nest Protect MCP Server MCP server in PolicyLayer and add a rule for search_mcp_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 Nest Protect MCP Server. Nothing to install.
search_mcp_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_mcp_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_mcp_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_mcp_tools is provided by the Nest Protect MCP Server MCP server (sandraschi/nest-protect-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 →