AI agents use pptx_edit_table_cell to create or update resources in Pptx — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Pptx environment.
This tool modifies existing data (table cell content and formatting) within a presentation file, but the changes are reversible—cells can be re-edited or the file discarded. It does not delete data irreversibly, execute arbitrary code, move money, or retrieve data without side effects.
From the tool's definition The tool 'pptx_edit_table_cell' modifies the text and formatting of a table cell within a PowerPoint presentation. The description explicitly states it can 'edit' and the verb 'edit' indicates data modification.
Attacks that exploit this kind of access
Edit a single table cell's text and formatting. It is categorised as a Write tool in the Pptx MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Pptx MCP server in PolicyLayer and add a rule for pptx_edit_table_cell: 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 Pptx. Nothing to install.
pptx_edit_table_cell 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 pptx_edit_table_cell 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 pptx_edit_table_cell. 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.
pptx_edit_table_cell is provided by the Pptx MCP server (knorq-ai/pptx-mcp-server). 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 →