AI agents use unmerge_cells 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.
Unmerging cells is a reversible modification to Excel formatting and structure. It changes how cells are organized but does not delete data, execute code, or create financial/destructive effects. This is a standard Write operation typical of spreadsheet editing tools. The severity is low because the change is easily reversible and has minimal business impact.
From the tool's definition Tool name 'unmerge_cells' and description 'Unmerge previously merged cells' indicate a cell formatting operation that modifies spreadsheet structure reversibly.
Attacks that exploit this kind of access
Unmerge previously merged 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 unmerge_cells: 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.
unmerge_cells 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 unmerge_cells 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 unmerge_cells. 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.
unmerge_cells 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 →