This record as markdown: /tools/deepl/get-source-languages.md
What get-source-languages does on DeepL
AI agents call get-source-languages to retrieve information from DeepL without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why get-source-languages is rated Low
This tool retrieves and returns a static list of available source languages from the DeepL service. It is a pure query operation with no ability to modify, delete, or execute actions. The data returned is informational metadata about service capabilities, making it a low-severity Read operation.
From the tool's definition Tool name 'get-source-languages' and description 'Get list of available source languages' indicate a retrieval operation that returns configuration/metadata about supported languages with no side effects.
Attacks that exploit this kind of access
The rule that runs get-source-languages safely
PolicyLayer is an MCP gateway: it sits between your AI agents and DeepL, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For get-source-languages, this is the rule to start with:
get-source-languages is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect DeepL, apply this rule, and every get-source-languages call is checked against it from then on.
Questions about get-source-languages
Get list of available source languages. It is categorised as a Read tool in the DeepL MCP Server, which means it retrieves data without modifying state.
Register the DeepL MCP server in PolicyLayer and add a rule for get-source-languages: 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. Nothing to install.
get-source-languages 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 get-source-languages 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 get-source-languages. 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.
get-source-languages is provided by the DeepL MCP server (@deepl-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on DeepL, and thousands of servers like it.
This server
Across the catalogue