Merge cells in a Google Sheet
AI agents use sheets_merge_cells to create or update resources in Mcp Gsheets — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mcp Gsheets environment.
Merging cells is a data formatting operation that modifies the spreadsheet structure. While reversible (cells can be unmerged), it constitutes a Write action as it changes the state of the sheet. It's not Read (no query), not Execute (no code execution), not Destructive (reversible), not Financial.
From the tool's definition sheets_merge_cells: 'Merge cells in a Google Sheet' - modifies cell formatting and structure by combining multiple cells into one, which is a reversible write operation.
Attacks that exploit this kind of access
Merge cells in a Google Sheet. It is categorised as a Write tool in the Mcp Gsheets MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mcp Gsheets MCP server in PolicyLayer and add a rule for sheets_merge_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 Mcp Gsheets. Nothing to install.
sheets_merge_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 sheets_merge_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 sheets_merge_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.
sheets_merge_cells is provided by the Mcp Gsheets MCP server (mcp-gsheets). 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 →