ファイルやディレクトリを検索します
AI agents call find_file to retrieve information from Claude MCP Server Integration without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves information about files and directories without modifying, executing, or deleting anything. It is a pure read operation analogous to filesystem search utilities (find, ls). The blast radius of misuse is minimal—an agent might discover sensitive file paths but cannot directly access, modify, or delete them.
From the tool's definition Tool name 'find_file' and description 'ファイルやディレクトリを検索します' (searches for files and directories) indicate a search/query operation with no side effects.
Attacks that exploit this kind of access
ファイルやディレクトリを検索します. It is categorised as a Read tool in the Claude MCP Server Integration MCP Server, which means it retrieves data without modifying state.
Register the Claude MCP Server Integration MCP server in PolicyLayer and add a rule for find_file: 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 Claude MCP Server Integration. Nothing to install.
find_file 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 find_file 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 find_file. 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.
find_file is provided by the Claude MCP Server Integration MCP server (mokemoke0821/claude-mcp-integration). 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 →