List every LLM the workspace can call through APIClaw — Anthropic, OpenAI, xAI/Grok, Groq, Mistral, Together, Cohere, Replicate, OpenRouter (800+ more), and any provider routed via the unified gateway. Returns OpenAI-compatible model objects.
AI agents call list_models to retrieve information from APIClaw without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and returns information about available LLM models within the workspace. It performs a read-only lookup operation with no capability to modify, execute code, delete data, or move funds. The function is informational, allowing an agent to discover what models are accessible.
From the tool's definition Tool description states it 'List every LLM the workspace can call' and 'Returns OpenAI-compatible model objects.' The verb 'list' and the action of returning model metadata indicates retrieval without side effects.
Risk signalsBulk/mass operation — affects multiple targets
Documented attack patterns abuse exactly the kind of access list_models gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and APIClaw, and nothing reaches the server without passing your rules. This is the rule we recommend for list_models:
{
"version": "1",
"default": "deny",
"tools": {
"list_models": {}
}
}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.
List every LLM the workspace can call through APIClaw — Anthropic, OpenAI, xAI/Grok, Groq, Mistral, Together, Cohere, Replicate, OpenRouter (800+ more), and any provider routed via the unified gateway. Returns OpenAI-compatible model objects. It is categorised as a Read tool in the APIClaw MCP Server, which means it retrieves data without modifying state.
Register the APIClaw MCP server in PolicyLayer and add a rule for 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 APIClaw. Nothing to install.
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 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 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.
list_models is provided by the APIClaw MCP server (nordsym/apiclaw). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from APIClaw, 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.
24 APIClaw tools catalogued and risk-classified — across an index of 43,000+ MCP servers.