Search for code patterns across the codebase using grep-like functionality.
AI agents call search_code to retrieve information from Claude Code Control MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries code patterns without creating, modifying, executing, or deleting data. It has no side effects beyond returning search results. Despite being on a server that includes execute_code_task, run_commands, and modify_files (which pose higher risks), search_code itself is a harmless read operation with minimal blast radius if misused by an agent.
From the tool's definition Tool name 'search_code' and description 'Search for code patterns across the codebase using grep-like functionality' indicates read-only operations. Grep is a standard tool for searching/querying text without modification or execution.
Attacks that exploit this kind of access
Search for code patterns across the codebase using grep-like functionality. It is categorised as a Read tool in the Claude Code Control MCP MCP Server, which means it retrieves data without modifying state.
Register the Claude Code Control MCP server in PolicyLayer and add a rule for search_code: 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 Claude Code Control MCP. Nothing to install.
search_code 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_code 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_code. 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_code is provided by the Claude Code Control MCP server (marc-shade/claude-code-control-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 →