Search for a pattern in a large file with context lines. Supports regex and case-sensitive search.
AI agents call search_in_large_file to retrieve information from Large File MCP Server 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 data from files without any side effects. It does not modify, create, delete, or execute code. It fits the Read category definition: 'retrieves or queries data; no side effects (search, list, get, fetch).' The low severity reflects that search operations pose minimal risk even if misused by an AI agent.
From the tool's definition The tool 'search_in_large_file' is described as searching for a pattern in a large file with context lines, supporting regex and case-sensitive search. This is a retrieval operation with no modification, deletion, or code execution capabilities.
Documented attack patterns abuse exactly the kind of access search_in_large_file gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Large File MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for search_in_large_file:
{
"version": "1",
"default": "deny",
"tools": {
"search_in_large_file": {}
}
}search_in_large_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.
Search for a pattern in a large file with context lines. Supports regex and case-sensitive search. It is categorised as a Read tool in the Large File MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Large File MCP Server MCP server in PolicyLayer and add a rule for search_in_large_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 Large File MCP Server. Nothing to install.
search_in_large_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_large_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_large_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_large_file is provided by the Large File MCP Server MCP server (willianpinho/large-file-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Large File MCP Server, 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 Large File MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.