models__list_ai_models

［AI 模型下架與替代日程］列出 OpenAI、Anthropic（Claude）、Google（Gemini）模型與 API 功能的淘汰狀態、下架日與官方建議替代；可依公司、狀態、類型篩選。

SERVERAI 代理人任務中樞 SOURCEhttps://hub.penguindriver.com/mcp

Low RISK CLASS

Category Read

Parameters 30 required

Recommended Allowedsee the rule below

Registry record Grade D, identity unverified Pull the record →

This record as markdown: /tools/com-penguindriver-hub/models--list-ai-models.md

WHAT IT DOES

What models__list_ai_models does on AI 代理人任務中樞

AI agents call models__list_ai_models to retrieve information from AI 代理人任務中樞 without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

Parameter	Type	Required
`kind`	string	—
`status`	string	—
`provider`	string	—

Parameters from the server's own tool schema.

RISK

Why models__list_ai_models is rated Low

Even though models__list_ai_models only reads data, uncontrolled read access leaks sensitive information and racks up API costs: an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs models__list_ai_models safely

PolicyLayer is an MCP gateway: it sits between your AI agents and AI 代理人任務中樞, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For models__list_ai_models, this is the rule to start with:

models__list_ai_models Allowed

models__list_ai_models is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "models__list_ai_models": {}
  }
}

ALLOW ONLY THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect AI 代理人任務中樞, apply this rule, and every models__list_ai_models call is checked against it from then on.

FAQ

Questions about models__list_ai_models

What does the models__list_ai_models tool do? +

［AI 模型下架與替代日程］列出 OpenAI、Anthropic（Claude）、Google（Gemini）模型與 API 功能的淘汰狀態、下架日與官方建議替代；可依公司、狀態、類型篩選。. It is categorised as a Read tool in the AI 代理人任務中樞 MCP Server, which means it retrieves data without modifying state.

What parameters does models__list_ai_models accept? +

models__list_ai_models accepts 3 parameters: kind, status, provider. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on models__list_ai_models? +

Register the AI 代理人任務中樞 MCP server in PolicyLayer and add a rule for models__list_ai_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 AI 代理人任務中樞. Nothing to install.

What risk level is models__list_ai_models? +

models__list_ai_models is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit models__list_ai_models? +

Yes. Add a rate_limit block to the models__list_ai_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.

How do I block models__list_ai_models completely? +

Set action: deny in the PolicyLayer policy for models__list_ai_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.

What MCP server provides models__list_ai_models? +

models__list_ai_models is provided by the AI 代理人任務中樞 MCP server (https://hub.penguindriver.com/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on AI 代理人任務中樞, and thousands of servers like it.

This server

All 174 AI 代理人任務中樞 tools →

Across the catalogue

list_symbols on ACE-MCP →aiva_list_affiliates on AIVA MCP Server → The MCP Attack Database →

Guides

Roll out MCP under one policy →Data exfiltration →MCP token cost →