Uploads a local document file for DeepL document translation and returns document_id/document_key.
AI agents use upload_document to create or update resources in DeepL MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your DeepL MCP Server environment.
An AI agent can call upload_document faster than any human can review — one bad instruction and it creates or modifies resources in DeepL MCP Server by the hundred, each call as confident as the last.
Attacks that exploit this kind of access
Uploads a local document file for DeepL document translation and returns document_id/document_key. It is categorised as a Write tool in the DeepL MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the DeepL MCP Server MCP server in PolicyLayer and add a rule for upload_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 DeepL MCP Server. Nothing to install.
upload_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 upload_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 upload_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.
upload_document is provided by the DeepL MCP Server MCP server (watchdealer-pavel/deepl-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.