Export query results to various formats (CSV, JSON)
AI agents use export_query to create or update resources in MCP Database Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MCP Database Server environment.
This tool creates new files or data exports (CSV, JSON formats) from query results, which is a reversible write operation. It doesn't execute arbitrary code (Execute), doesn't permanently delete data (Destructive), doesn't move money (Financial), and doesn't merely read data without side effects (Read).
From the tool's definition The tool 'export_query' exports query results to various formats (CSV, JSON), which involves creating and writing output files or data exports. This is a data creation/modification action.
Attacks that exploit this kind of access
Export query results to various formats (CSV, JSON). It is categorised as a Write tool in the MCP Database Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the MCP Database Server MCP server in PolicyLayer and add a rule for export_query: 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 MCP Database Server. Nothing to install.
export_query 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 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. 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 is provided by the MCP Database Server MCP server (msathiyakeerthi/mcp-database-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 →