Scan project for locale files (JSON, ARB, .strings, .xcstrings, .stringsdict), detect i18n framework (next-intl, i18next, react-intl, flutter, ios-macos, generic), and return structured information about available translations.
AI agents call list_local_locales to retrieve information from Langapi without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a scanning and detection operation to gather information about locale files and i18n framework configuration in a project. It has no side effects—it does not create, modify, delete, or execute any code. It falls squarely into the Read category as it simply queries and returns structured data about the current state of locale files and detected framework type.
From the tool's definition Tool name is 'list_local_locales' and description states it will 'Scan project for locale files' and 'return structured information about available translations'.
Attacks that exploit this kind of access
Scan project for locale files (JSON, ARB, .strings, .xcstrings, .stringsdict), detect i18n framework (next-intl, i18next, react-intl, flutter, ios-macos, generic), and return structured information about available translations. It is categorised as a Read tool in the Langapi MCP Server, which means it retrieves data without modifying state.
Register the Langapi MCP server in PolicyLayer and add a rule for list_local_locales: 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 Langapi. Nothing to install.
list_local_locales 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_local_locales 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_local_locales. 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_local_locales is provided by the Langapi MCP server (tedyhub/langapi-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 →