将表数据导出到CSV文件
AI agents call export_to_csv to retrieve information from PySqlitMCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool reads data from a database table and writes it to a CSV file. While it creates a file on disk, its primary action is reading/exporting existing data without modifying the source database. The blast radius is low since it doesn't alter database contents, though it could expose sensitive data via the exported file.
From the tool's definition 将表数据导出到CSV文件 (Export table data to CSV file)
Attacks that exploit this kind of access
将表数据导出到CSV文件. It is categorised as a Read tool in the PySqlitMCP MCP Server, which means it retrieves data without modifying state.
Register the PySqlit MCP server in PolicyLayer and add a rule for export_to_csv: 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 PySqlitMCP. Nothing to install.
export_to_csv 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_to_csv 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_to_csv. 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_to_csv is provided by the PySqlit MCP server (python51888/pysqlitmcp). 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 →