This record as markdown: /tools/deepdepcat/export-document.md
What export_document does on Deepdepcat
AI agents use export_document to create or update resources in Deepdepcat, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Deepdepcat environment.
Why export_document is rated Medium
Exports documents to external formats; reversible but alters stored state and permits data exfiltration risk.
From the tool's definition export_document; creates/outputs document in new format
Attacks that exploit this kind of access
The rule that runs export_document safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Deepdepcat, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For export_document, this is the rule to start with:
export_document stays usable, but capped: an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Deepdepcat, apply this rule, and every export_document call is checked against it from then on.
Questions about export_document
导出文档。. It is categorised as a Write tool in the Deepdepcat MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Deepdepcat MCP server in PolicyLayer and add a rule for export_document: 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 Deepdepcat. Nothing to install.
export_document 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_document 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_document. 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_document is provided by the Deepdepcat MCP server (hanmirage/deepdepcat). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Deepdepcat, and thousands of servers like it.
This server
Across the catalogue