export_tmx_file
AI agents use export_tmx_file to create or update resources in Xliff Processor — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Xliff Processor environment.
Exporting files creates or writes data artifacts (TMX files) that can be used downstream, making this a Write operation rather than Read. While export operations are typically reversible, they generate new data objects.
From the tool's definition Tool name 'export_tmx_file' indicates file creation/output of TMX translation data. Sibling tools include 'export_xliff_file', 'process_tmx', and 'replace_xliff_targets', suggesting this server manipulates and exports translation files.
Attacks that exploit this kind of access
export_tmx_file. It is categorised as a Write tool in the Xliff Processor MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Xliff Processor MCP server in PolicyLayer and add a rule for export_tmx_file: 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 Xliff Processor. Nothing to install.
export_tmx_file 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_tmx_file 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_tmx_file. 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_tmx_file is provided by the Xliff Processor MCP server (langlink-localization/xliff-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 →