Get SANDBOX translations that need quality improvement. Reads quality scores from sandbox (not production). Returns all non-green/problematic translations with full context, values, and quality details. Use this to find translations that need better context, improved translation quality, or both....
AI agents call get_translations_needing_attention to retrieve information from Localization without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
limit | integer | — | Max items to return (default: 50) |
namespace | string | Yes | Namespace slug |
projectSlug | string | Yes | Project slug |
qualityLevels | string | — | Comma-separated quality levels to include (default: 'yellow,red'). Options: green, yellow, red, unchecked, needs_context, context_required, context_useful. |
includeUnchecked | boolean | — | Also include items not yet quality-checked |
Parameters from the server's own tool schema.
This tool retrieves and queries translation data from a sandbox environment to identify items needing attention. It has no side effects—it neither creates, modifies, deletes, nor executes external operations. The phrase 'The agent can then inspect each item and decide' indicates the tool itself only provides information for human or downstream decision-making.
From the tool's definition The tool 'Get SANDBOX translations that need quality improvement' explicitly performs a read operation: 'Reads quality scores from sandbox', 'Returns all non-green/problematic translations with full context, values, and quality details.' It retrieves data for…
Attacks that exploit this kind of access
Get SANDBOX translations that need quality improvement. Reads quality scores from sandbox (not production). Returns all non-green/problematic translations with full context, values, and quality details. Use this to find translations that need better context, improved translation quality, or both. The agent can then inspect each item and decide: add/improve context, improve translation, or both. It is categorised as a Read tool in the Localization MCP Server, which means it retrieves data without modifying state.
get_translations_needing_attention accepts 5 parameters: limit, namespace, projectSlug, qualityLevels, includeUnchecked. Required: namespace, projectSlug. The full parameter table on this page comes from the server's own tool schema.
Register the Localization MCP server in PolicyLayer and add a rule for get_translations_needing_attention: 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 Localization. Nothing to install.
get_translations_needing_attention 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_translations_needing_attention 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_translations_needing_attention. 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_translations_needing_attention is provided by the Localization MCP server (localization-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 →