AI agents call search_tools to retrieve information from Mcpcute 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 about available tools without side effects. It performs a search operation, which is a read-only retrieval of metadata. There is no indication of data modification, code execution, or irreversible operations. The low severity reflects minimal blast radius if misused—an agent could only retrieve information about tools, not invoke or alter them.
From the tool's definition Tool name 'search_tools' and description indicating it searches/lists available tools without modification. The sibling tools include 'list_tools', 'list_mcps', and 'get_tool_details', all of which are read-only information retrieval operations.
Attacks that exploit this kind of access
[EXPLICIT ONLY - Do NOT use unless the user explicitly mentions. It is categorised as a Read tool in the Mcpcute MCP Server, which means it retrieves data without modifying state.
Register the Mcpcute 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 Mcpcute. 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 Mcpcute MCP server (zhigang1992/mcpcute). 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 →