AI agents call export_table_1_csv to retrieve information from MCP-Maker without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool reads data from a table and exports it as a CSV string. This is a read/query operation with no writes, executions, or deletions. Severity is medium because bulk data export can expose sensitive information depending on what 'table_1' contains, and the server's purpose is to connect AI clients to arbitrary data sources.
From the tool's definition Export 'table_1' data as CSV string — this retrieves and serializes table data into a CSV format with no stated side effects.
Attacks that exploit this kind of access
Export 'table_1' data as CSV string. It is categorised as a Read tool in the MCP-Maker MCP Server, which means it retrieves data without modifying state.
Register the MCP-Maker MCP server in PolicyLayer and add a rule for export_table_1_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 MCP-Maker. Nothing to install.
export_table_1_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_table_1_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_table_1_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_table_1_csv is provided by the MCP-Maker MCP server (mralihasan/mcp-maker). 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 →