Browse translation entries in a namespace. Use env='sandbox' (default) to see the working sandbox view, or env='production' to see what is currently live. Supports pagination, full-text search, and quality/context filtering. Use missingLocale to find keys missing a value for a specific locale. Us...
AI agents call list_translations 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 |
|---|---|---|---|
env | string | — | Which environment to read from. Default: sandbox (the editable working copy). |
page | integer | — | Page number (default: 1) |
limit | integer | — | Items per page (default: 50, max: 100) |
search | string | — | Search string (min 2 chars) — searches keys and values |
sortBy | string | — | Sort field |
namespace | string | Yes | Namespace slug (e.g. 'common', 'backoffice') |
sortOrder | string | — | Sort direction |
projectSlug | string | Yes | Project slug |
qualityLevel | string | — | Filter by quality level. 'needs_context' = context required or useful but missing. 'context_required' / 'context_useful' filter separately. |
searchLocale | string | — | Restrict value search to a specific locale (e.g. 'en') |
missingLocale | string | — | Return only entries where this locale has no value or an empty value. Use this to find gaps after adding a new locale. |
Parameters from the server's own tool schema.
This tool retrieves and queries translation data with filtering and search capabilities. It has no side effects—it only reads from sandbox or production environments without modifying, deleting, or executing anything. The blast radius of misuse is minimal; an agent could only over-query or retrieve data it shouldn't see, which is a containment/access control issue rather than a destructive one.
From the tool's definition Tool description states 'Browse translation entries' with capabilities limited to 'pagination, full-text search, and quality/context filtering' and finding keys by locale or quality level. No create, modify, delete, or execute operations are described.
Risk signalsHigh parameter count (11 properties)
Attacks that exploit this kind of access
Browse translation entries in a namespace. Use env='sandbox' (default) to see the working sandbox view, or env='production' to see what is currently live. Supports pagination, full-text search, and quality/context filtering. Use missingLocale to find keys missing a value for a specific locale. Use qualityLevel to filter by worst quality level across locales. Use qualityLevel 'needs_context' to find keys where context is required or useful but missing. It is categorised as a Read tool in the Localization MCP Server, which means it retrieves data without modifying state.
list_translations accepts 11 parameters: env, page, limit, search, sortBy, namespace, sortOrder, projectSlug, qualityLevel, searchLocale, missingLocale. 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 list_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 Localization. Nothing to install.
list_translations 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 list_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 list_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.
list_translations 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 →