AI agents use merge_table_cells to create or update resources in Google — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Google environment.
Merging table cells modifies the structure and formatting of a Google Doc table in a reversible manner. This is a write operation—it changes document state but can be undone (cells can be unmerged). It does not delete data irreversibly, execute arbitrary code, or trigger financial transactions.
From the tool's definition Tool name 'merge_table_cells' and context within google-mcp server that provides 'cell-level edits' and 'formatting' to Google Docs. Description states it 'merges cells in a Google Doc table,' which is a formatting modification operation.
Attacks that exploit this kind of access
Merge cells in a Google Doc table. It is categorised as a Write tool in the Google MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Google MCP server in PolicyLayer and add a rule for merge_table_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 Google. Nothing to install.
merge_table_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 merge_table_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 merge_table_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.
merge_table_cells is provided by the Google MCP server (ztgluis/google-mcp). 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 →