Retrieve the translated file once async generation is confirmed complete (status = COMPLETED from tms_get_async_request). Returns file content as base64 (bytes_base64) plus content_type and file_name. Optionally saves the decoded file to disk via output_path. (GET /api2/v3/projects/{projectUid}/j...
AI agents call tms_download_target_file_by_async_request to retrieve information from Phrase without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and downloads completed translation output. While it can optionally save to disk via output_path, this is a local file write, not a modification of the localization project data. The core operation is a read/retrieval of existing translated content that has already been confirmed complete. No data is created, modified, deleted, or destroyed in the Phrase system.
From the tool's definition Tool description explicitly states 'Retrieve the translated file' and 'Returns file content as base64...'. The HTTP method is GET. The action is retrieving already-generated translated content with no side effects on the localization system itself.
Attacks that exploit this kind of access
Retrieve the translated file once async generation is confirmed complete (status = COMPLETED from tms_get_async_request). Returns file content as base64 (bytes_base64) plus content_type and file_name. Optionally saves the decoded file to disk via output_path. (GET /api2/v3/projects/{projectUid}/jobs/{jobUid}/downloadTargetFile/{asyncRequestId}). It is categorised as a Read tool in the Phrase MCP Server, which means it retrieves data without modifying state.
Register the Phrase MCP server in PolicyLayer and add a rule for tms_download_target_file_by_async_request: 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 Phrase. Nothing to install.
tms_download_target_file_by_async_request 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 tms_download_target_file_by_async_request 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 tms_download_target_file_by_async_request. 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.
tms_download_target_file_by_async_request is provided by the Phrase MCP server (phrase-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 →