AI agents call search_files to retrieve information from Mcp Ssh without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
File search operations retrieve or query file system data without modifying, executing, or deleting anything. The empty description reduces confidence slightly, but the tool name and context of a system management server strongly indicate this is a benign read operation for locating files.
From the tool's definition Tool named 'search_files' with empty description. Given the server's purpose (remote Linux/Unix management via SSH) and sibling tools that include read-only operations like 'analyze_log_errors' and 'check_disk_health', search_files is clearly a read-only file…
Attacks that exploit this kind of access
search_files. It is categorised as a Read tool in the Mcp Ssh MCP Server, which means it retrieves data without modifying state.
Register the Mcp Ssh 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 Ssh. 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 Ssh MCP server (zhouxiangjing/mcp-ssh). 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 →