Recursively search for files and directories matching a pattern.
AI agents call search_files to retrieve information from Server Sequential Thinking without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool searches the filesystem for matching files and directories. Search operations retrieve information without modifying, deleting, or executing anything. The action is read-only and non-destructive, making it a Read category tool with low severity risk.
From the tool's definition Tool name 'search_files' and description 'Recursively search for files and directories matching a pattern' indicate a query/retrieval operation with no side effects.
Attacks that exploit this kind of access
Recursively search for files and directories matching a pattern. It is categorised as a Read tool in the Server Sequential Thinking MCP Server, which means it retrieves data without modifying state.
Register the Server Sequential Thinking 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 Server Sequential Thinking. 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 Server Sequential Thinking MCP server (@modelcontextprotocol/server-sequential-thinking). 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 →