AI agents call atlas_list_models to retrieve information from Gemini Skill without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or lists data (available models) with no side effects, mutations, or state changes. It is a pure read operation that falls clearly under the Read category. Severity is low because listing models poses minimal risk even if misused by an AI agent.
From the tool's definition Tool name 'atlas_list_models' and description 'Get list of models visible to current API Key' (translated from Chinese: '获取 Atlas Cloud 当前 API Key 可见的模型列表') indicates a retrieval operation that queries available models without modifying any state.
Documented attack patterns abuse exactly the kind of access atlas_list_models gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Gemini Skill, and nothing reaches the server without passing your rules. This is the rule we recommend for atlas_list_models:
{
"version": "1",
"default": "deny",
"tools": {
"atlas_list_models": {}
}
}atlas_list_models 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.
获取 Atlas Cloud 当前 API Key 可见的模型列表（OpenAI 兼容接口）. It is categorised as a Read tool in the Gemini Skill MCP Server, which means it retrieves data without modifying state.
Register the Gemini Skill MCP server in PolicyLayer and add a rule for atlas_list_models: 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 Gemini Skill. Nothing to install.
atlas_list_models 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 atlas_list_models 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 atlas_list_models. 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.
atlas_list_models is provided by the Gemini Skill MCP server (wjz-p/gemini-skill). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 21 Gemini Skill tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
21 Gemini Skill tools catalogued and risk-classified — across an index of 42,500+ MCP servers.