Export all pages in a flow to a CSV string.
AI agents use pages_to_dataframe to create or update resources in Dialogflow CX MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Dialogflow CX MCP Server environment.
An AI agent can call pages_to_dataframe faster than any human can review — one bad instruction and it creates or modifies resources in Dialogflow CX MCP Server by the hundred, each call as confident as the last.
Attacks that exploit this kind of access
Export all pages in a flow to a CSV string. It is categorised as a Write tool in the Dialogflow CX MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Dialogflow CX MCP Server MCP server in PolicyLayer and add a rule for pages_to_dataframe: 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 Dialogflow CX MCP Server. Nothing to install.
pages_to_dataframe 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 pages_to_dataframe 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 pages_to_dataframe. 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.
pages_to_dataframe is provided by the Dialogflow CX MCP Server MCP server (yash-kavaiya/conversation_agents_mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.