Searches for regex patterns in a file, returning matches with optional context.
AI agents call search_in_file to retrieve information from MCP Tools without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a query operation on file contents without creating, modifying, deleting, or executing code. It is purely informational and retrieves data matching a pattern. The low severity reflects minimal blast radius—an AI agent cannot cause harm by searching files, only by what it does with the information retrieved.
From the tool's definition Tool description states it 'Searches for regex patterns in a file, returning matches with optional context.' The verb 'searches' and 'returning' indicate data retrieval with no modification or side effects.
Documented attack patterns abuse exactly the kind of access search_in_file gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MCP Tools, and nothing reaches the server without passing your rules. This is the rule we recommend for search_in_file:
{
"version": "1",
"default": "deny",
"tools": {
"search_in_file": {}
}
}search_in_file is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Searches for regex patterns in a file, returning matches with optional context. It is categorised as a Read tool in the MCP Tools MCP Server, which means it retrieves data without modifying state.
Register the MCP Tools MCP server in PolicyLayer and add a rule for search_in_file: 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 MCP Tools. Nothing to install.
search_in_file 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_in_file 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_in_file. 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_in_file is provided by the MCP Tools MCP server (zbigniewtomanek/my-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from MCP Tools, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
6 MCP Tools tools catalogued and risk-classified — across an index of 43,000+ MCP servers.