search_tools
AI agents call search_tools to retrieve information from Code Execution MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The name 'search_tools' combined with context of a tooling server (evidenced by sibling tools like 'list_skills', 'get_tool_definition', 'list_tool_categories') indicates this retrieves metadata about available tools rather than executing operations. This is a Read operation with minimal blast radius.
From the tool's definition Tool name 'search_tools' indicates querying/discovery of available tools. No description provided, but the sibling tools include 'list_tools_categories' and 'list_skill', suggesting this is a tool enumeration/discovery function with no side effects.
Attacks that exploit this kind of access
search_tools. It is categorised as a Read tool in the Code Execution MCP MCP Server, which means it retrieves data without modifying state.
Register the Code Execution 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 Code Execution MCP. 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 Code Execution MCP server (marc-shade/code-execution-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 →