AI agents use create_chart 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.
This tool creates a new visualization object within a worksheet. It is reversible (charts can be removed), causes no external side effects, and does not execute arbitrary code or delete data. It fits the Write category: it creates or modifies data/objects within the workbook.
From the tool's definition "Create a chart in the worksheet" involves creating new structured data artifacts within an Excel workbook. The sibling tools include create_workbook, create_worksheet, and create_pivot_table—all Write-category operations.
Attacks that exploit this kind of access
Create a chart in the worksheet. 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 create_chart: 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.
create_chart 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 create_chart 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 create_chart. 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.
create_chart 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 →