AI agents use save_translations to create or update resources in Paraglide — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Paraglide environment.
save_translations modifies translation data for a specific locale by persisting changes to the project, which is a write operation. It does not delete data (would be Destructive), execute arbitrary code (would be Execute), nor handle financial transactions (would be Financial).
From the tool's definition Tool description states 'write them to the project' and 'Save translated messages', indicating creation/modification of translation data files.
Attacks that exploit this kind of access
Save translated messages for one target locale and write them to the project. It is categorised as a Write tool in the Paraglide MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Paraglide MCP server in PolicyLayer and add a rule for save_translations: 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 Paraglide. Nothing to install.
save_translations 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 save_translations 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 save_translations. 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.
save_translations is provided by the Paraglide MCP server (weshaze/paraglide-mcp). 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 →