AI agents use format_range to create or update resources in Excel — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Excel environment.
Formatting cells (font, color, alignment, etc.) is a reversible modification that changes the presentation of data but not its underlying structure or values. This is a Write operation—it modifies state but can be undone. Severity is medium because formatting changes could obscure critical data or create misleading presentations, but the data itself remains intact and recoverable.
From the tool's definition Tool name 'format_range' and description 'Apply formatting to a range of cells' indicate modification of cell properties without creating or deleting data content.
Attacks that exploit this kind of access
Apply formatting to a range of cells. It is categorised as a Write tool in the Excel MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Excel MCP server in PolicyLayer and add a rule for format_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. Nothing to install.
format_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 format_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 format_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.
format_range is provided by the Excel MCP server (shmaxi/excel-mcp-server-node). 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 →