Search file and directory paths by regex inside an allowed project root.
AI agents call mcp_search_files to retrieve information from Local Code without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only searches and lists file/directory paths matching a regex pattern within allowed project roots. It has no capability to modify, delete, execute, or access financial systems. The operation is read-only with minimal blast radius—worst case an attacker gains knowledge of file structure within already-allowed folders.
From the tool's definition The tool 'search file and directory paths by regex' performs a search operation that retrieves information about files and directories without modifying, deleting, or executing code.
Risk signalsAdmin/system-level operation
Attacks that exploit this kind of access
Search file and directory paths by regex inside an allowed project root. It is categorised as a Read tool in the Local Code MCP Server, which means it retrieves data without modifying state.
Register the Local Code MCP server in PolicyLayer and add a rule for mcp_search_files: 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 Local Code. Nothing to install.
mcp_search_files 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 mcp_search_files 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 mcp_search_files. 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.
mcp_search_files is provided by the Local Code MCP server (js190-prog/local-code-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 →