ワークシートをCSVファイルにエクスポートします
AI agents use export_to_csv to create or update resources in Excel MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Excel MCP Server environment.
Exporting data to CSV creates a new file or overwrites an existing one, which is a write operation. While not destructive (the original worksheet remains), it does create/modify file system state. Severity is medium because unintended CSV exports could expose sensitive spreadsheet data to unintended locations or formats, but the operation is reversible (the file can be deleted).
From the tool's definition Tool name 'export_to_csv' and description 'ワークシートをCSVファイルにエクスポート' (export worksheet to CSV file) indicates creation of a new file/data output.
Attacks that exploit this kind of access
ワークシートをCSVファイルにエクスポートします. It is categorised as a Write tool in the Excel MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Excel MCP Server MCP server in PolicyLayer and add a rule for export_to_csv: 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 Excel MCP Server. Nothing to install.
export_to_csv is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the export_to_csv 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 export_to_csv. 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.
export_to_csv is provided by the Excel MCP Server MCP server (superpyonchix/excel_mcp_server). 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 →