Export query results in various formats (JSON, CSV)
AI agents use export_query_results to create or update resources in Vertica MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Vertica MCP Server environment.
Export operations create new files or data artifacts (CSV, JSON) and constitute a Write action—data is being extracted and serialized into a new form. While the underlying query is Read, the export itself materializes and persists data in a new format.
From the tool's definition Tool description states it 'Export query results in various formats (JSON, CSV)' — an export operation that writes data to a new artifact or file format, creating or modifying output.
Attacks that exploit this kind of access
Export query results in various formats (JSON, CSV). It is categorised as a Write tool in the Vertica MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Vertica MCP Server MCP server in PolicyLayer and add a rule for export_query_results: 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 Vertica MCP Server. Nothing to install.
export_query_results 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 export_query_results 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_query_results. 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_query_results is provided by the Vertica MCP Server MCP server (smith-nathanh/vertica-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 →