AI agents call deepl_translate_text to retrieve information from UnClick without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
text | object | Yes | Text or array of texts to translate (max 50 texts per call) |
auth_key | string | Yes | DeepL Auth Key from deepl.com. Free tier keys end with :fx. |
formality | string | — | Formality level (supported in some languages) |
source_lang | string | — | Source language code (auto-detected if omitted) |
target_lang | string | Yes | Target language code (e.g. EN-US, EN-GB, DE, FR, JA, ZH, ES) |
tag_handling | string | — | Enable tag handling |
preserve_formatting | boolean | — | Preserve original formatting |
Parameters from the server's own tool schema.
This tool retrieves and processes text to produce translated output. It does not create, modify, delete, or irreversibly change any data in external systems. It does not execute code, trigger external operations with side effects, or involve financial transactions.
From the tool's definition Tool description states it 'translates text into another language using DeepL's neural translation engine.' Translation is a data transformation service that reads input text and returns translated output with no side effects, data modification, deletion,…
Attacks that exploit this kind of access
Translate text into another language using DeepL's neural translation engine. It is categorised as a Read tool in the UnClick MCP Server, which means it retrieves data without modifying state.
deepl_translate_text accepts 7 parameters: text, auth_key, formality, source_lang, target_lang, tag_handling, preserve_formatting. Required: text, auth_key, target_lang. The full parameter table on this page comes from the server's own tool schema.
Register the UnClick MCP server in PolicyLayer and add a rule for deepl_translate_text: 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 UnClick. Nothing to install.
deepl_translate_text 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 deepl_translate_text 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 deepl_translate_text. 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.
deepl_translate_text is provided by the UnClick MCP server (@unclick/mcp-server). 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 →