AI agents call detectLanguage to retrieve information from Translate without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a read-only operation that analyzes text to determine its language and returns the result. It has no side effects, does not execute code or commands, does not modify data, and does not involve financial transactions. The blast radius of misuse is minimal—at worst, an AI could analyze private text to identify languages, but this causes no irreversible harm.
From the tool's definition Tool name 'detectLanguage' and description '检测文本语言' (detect text language) indicate the tool analyzes input text and returns language identification metadata without modifying, executing, or deleting any data.
Attacks that exploit this kind of access
检测文本语言. It is categorised as a Read tool in the Translate MCP Server, which means it retrieves data without modifying state.
Register the Translate MCP server in PolicyLayer and add a rule for detectLanguage: 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 Translate. Nothing to install.
detectLanguage 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 detectLanguage 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 detectLanguage. 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.
detectLanguage is provided by the Translate MCP server (translate-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 →