Search for text pattern in files (grep-like functionality). Returns list of unique file paths containing the pattern. Recursively searches all subdirectories by default. Automatically skips node_modules, .git, dist, build directories and binary files for performance.
AI agents call search_content to retrieve information from MCP Local File Reader without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is fundamentally a read operation—it queries the file system to find files matching a pattern and returns results. While the recursive search across subdirectories and automatic filtering of common directories suggests broad scope, the tool has no side effects on the system.
From the tool's definition Tool performs text pattern searching with "grep-like functionality" and "returns list of unique file paths". Description explicitly states it "searches" and retrieves file paths, not modifying data.
Attacks that exploit this kind of access
Search for text pattern in files (grep-like functionality). Returns list of unique file paths containing the pattern. Recursively searches all subdirectories by default. Automatically skips node_modules, .git, dist, build directories and binary files for performance. It is categorised as a Read tool in the MCP Local File Reader MCP Server, which means it retrieves data without modifying state.
Register the MCP Local File Reader MCP server in PolicyLayer and add a rule for search_content: 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 Local File Reader. Nothing to install.
search_content 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_content 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_content. 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_content is provided by the MCP Local File Reader MCP server (yryuu/mcp-localfile-all-read). 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 →