Copy a range of cells to another location.
AI agents use copy_range 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.
Copying cell ranges is a reversible modification operation that creates or overwrites data in a worksheet. It does not delete data irreversibly (which would be Destructive) and does not execute arbitrary code (which would be Execute). It is a write operation that modifies workbook state.
From the tool's definition Tool name is 'copy_range' and description states it 'Copy[s] a range of cells to another location.' This operation creates a copy of data at a new location, modifying the target worksheet by adding or overwriting cells.
Attacks that exploit this kind of access
Copy a range of cells to another location. 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 copy_range: 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.
copy_range 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 copy_range 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 copy_range. 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.
copy_range is provided by the Excel MCP Server MCP server (thibaudvandendooren-acumen/excel-mcp-server-v2). 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 →