ファイルの自動分類・タグ付けを実行します
AI agents call classify_files 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 reads file properties/contents to classify them and applies metadata tags. While tagging constitutes a minor write operation, the primary function is analyzing and categorizing existing files without destructive or irreversible changes. However, tagging does technically modify metadata. Reconsidering: the tool applies tags (metadata writes) as its core function.
From the tool's definition Tool name 'classify_files' and description indicating automatic file classification and tagging. The action is to analyze and categorize files by applying metadata (tags), which does not modify file contents, delete files, or execute operations with side…
Attacks that exploit this kind of access
ファイルの自動分類・タグ付けを実行します. 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 classify_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 Claude MCP Server Integration. Nothing to install.
classify_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 classify_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 classify_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.
classify_files 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 →