Get the translation for a key from every loaded locale at once.
AI agents call get_all to retrieve information from Mcp Locator without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves translation data across multiple locales without modifying, creating, or deleting any state. It is a pure query operation that poses minimal risk if called by an AI agent, as it cannot alter files or system state.
From the tool's definition Tool description states 'Get the translation for a key' — a retrieval operation with no side effects. Server description confirms the purpose includes 'read and write' capabilities, and this tool's name and description indicate it only reads data ('get').
Risk signalsBulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
Get the translation for a key from every loaded locale at once. It is categorised as a Read tool in the Mcp Locator MCP Server, which means it retrieves data without modifying state.
Register the Mcp Locator MCP server in PolicyLayer and add a rule for get_all: 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 Mcp Locator. Nothing to install.
get_all 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_all 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_all. 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_all is provided by the Mcp Locator MCP server (tankonyako/mcp-locator). 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 →