Search files containing text
AI agents call search_files to retrieve information from MCP Filesystem Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a search operation to locate files matching text criteria. Search is inherently a retrieval operation with no side effects—it does not create, modify, delete, or execute anything. The blast radius of misuse is minimal: an agent could discover unintended files but cannot alter system state or execute code. Severity is low because even if an AI oversteps, it merely reads metadata and file locations.
From the tool's definition Tool name 'search_files' and description 'Search files containing text' indicate a query-only operation that retrieves matching files without modifying, executing code, or deleting data.
Attacks that exploit this kind of access
Search files containing text. It is categorised as a Read tool in the MCP Filesystem Server MCP Server, which means it retrieves data without modifying state.
Register the MCP Filesystem Server MCP server in PolicyLayer and add a rule for 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 MCP Filesystem Server. Nothing to install.
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 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 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.
search_files is provided by the MCP Filesystem Server MCP server (midsane/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 →