Search files by content with business intelligence
AI agents call filesystem_search to retrieve information from Chicken Business Management MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
filesystem_search performs a read-only operation that retrieves information by searching file contents. Despite being on a filesystem, it does not modify, delete, or execute—it only queries and returns matching results. This is consistent with Read category behavior.
From the tool's definition Tool description states 'Search files by content' and 'business intelligence'. The operation is a search/query action with no modification, deletion, or execution capabilities indicated.
Attacks that exploit this kind of access
Search files by content with business intelligence. It is categorised as a Read tool in the Chicken Business Management MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Chicken Business Management MCP Server MCP server in PolicyLayer and add a rule for filesystem_search: 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 Chicken Business Management MCP Server. Nothing to install.
filesystem_search 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 filesystem_search 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 filesystem_search. 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.
filesystem_search is provided by the Chicken Business Management MCP Server MCP server (psyger02/mcpserver). 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 →