AI agents call translate to retrieve information from YiGmMk/mcp without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Translation is a stateless, reversible data transformation with no side effects. It retrieves no sensitive data beyond what the user provides as input, executes no code or commands, and creates no persistent changes. The low severity reflects that misuse would only produce incorrect translations, with minimal blast radius.
From the tool's definition Tool description states '使用 gemini 翻译文本，中英文互译' (translate text using gemini, Chinese-English mutual translation). This is a read-only operation that transforms input text without modifying, deleting, or executing external operations.
Documented attack patterns abuse exactly the kind of access translate gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and YiGmMk/mcp, and nothing reaches the server without passing your rules. This is the rule we recommend for translate:
{
"version": "1",
"default": "deny",
"tools": {
"translate": {}
}
}translate is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
使用 gemini 翻译文本，中英文互译. It is categorised as a Read tool in the YiGmMk/mcp MCP Server, which means it retrieves data without modifying state.
Register the YiGmMk/ MCP server in PolicyLayer and add a rule for translate: 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 YiGmMk/mcp. Nothing to install.
translate 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 translate 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 translate. 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.
translate is provided by the YiGmMk/ MCP server (yigmmk/mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from YiGmMk/mcp, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
4 YiGmMk/mcp tools catalogued and risk-classified — across an index of 43,000+ MCP servers.