Check translation quality for multiple locales at once using AI. Accepts source English text and a locale-to-translation map. Returns per-locale quality score (1-100), level (green/yellow/red), and comment. Does NOT persist results — use check_entry_quality to persist. Usage is tracked per project.
AI agents call ai_quality_check 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 |
|---|---|---|---|
source | string | Yes | Source English text |
context | string | — | Context about where/how this key is used (max 1000 chars). Helps AI evaluate accuracy — especially for short/ambiguous strings. Describe: screen, UI element typ |
projectSlug | string | Yes | Project slug for usage tracking |
translations | object | Yes | Locale to translation map, e.g. { "uk": "Зберегти", "de": "Speichern" } |
Parameters from the server's own tool schema.
This tool performs analysis and quality assessment of translations without side effects. It reads input data and returns computed metrics (scores 1-100, level classifications, comments) but does not create, modify, delete, or persist any data. The explicit note that results are not persisted confirms no write operations occur. Usage tracking is metadata collection, not a data modification.
From the tool's definition Tool 'ai_quality_check' accepts source text and translations, returns quality scores, levels, and comments. Explicitly states 'Does NOT persist results' and is for checking/analyzing only. No modification, deletion, or execution of external operations.
Attacks that exploit this kind of access
Check translation quality for multiple locales at once using AI. Accepts source English text and a locale-to-translation map. Returns per-locale quality score (1-100), level (green/yellow/red), and comment. Does NOT persist results — use check_entry_quality to persist. Usage is tracked per project. It is categorised as a Read tool in the Localization MCP Server, which means it retrieves data without modifying state.
ai_quality_check accepts 4 parameters: source, context, projectSlug, translations. Required: source, projectSlug, translations. 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 ai_quality_check: 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.
ai_quality_check 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 ai_quality_check 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 ai_quality_check. 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.
ai_quality_check 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 →