AI agents call get_translation_batch to retrieve information from Paraglide without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves/queries untranslated messages for a specified locale without modifying, deleting, or executing any operations. It is a read-only operation consistent with data retrieval patterns. While the description is incomplete (ends with 'optionally'), the core function—fetching a batch of messages—clearly aligns with the Read category. No data is created, modified, deleted, or executed.
From the tool's definition Tool name 'get_translation_batch' and description 'Get the next batch of untranslated messages for a target locale' indicate a retrieval operation with no side effects.
Attacks that exploit this kind of access
Get the next batch of untranslated messages for a target locale (optionally. It is categorised as a Read tool in the Paraglide MCP Server, which means it retrieves data without modifying state.
Register the Paraglide MCP server in PolicyLayer and add a rule for get_translation_batch: 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.
get_translation_batch 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_translation_batch 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_translation_batch. 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_translation_batch 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 →