Export data from a Sigma workbook or dataset in CSV/JSON format
AI agents call export_data to retrieve information from Sigma MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Exporting data is fundamentally a read operation: it queries/fetches data from a workbook or dataset and renders it in a portable format. No creation, modification, deletion, or financial action is described. Severity is medium because exported data could include sensitive analytics or business data, representing a data-exfiltration risk if misused, but the action itself is non-destructive and reversible.
From the tool's definition 'Export data from a Sigma workbook or dataset in CSV/JSON format' — retrieves and serializes existing data into CSV/JSON, no modification implied
Attacks that exploit this kind of access
Export data from a Sigma workbook or dataset in CSV/JSON format. It is categorised as a Read tool in the Sigma MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Sigma MCP Server MCP server in PolicyLayer and add a rule for export_data: 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 Sigma MCP Server. Nothing to install.
export_data is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the export_data 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 export_data. 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.
export_data is provided by the Sigma MCP Server MCP server (ja2z/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 →