ai_models

Manage local AI models. List installed, pull new ones, get model info. Example: ai_models({ action:

SERVER0nmcp SOURCE0nmcp

Low RISK CLASS

Category Read

Parameters 00 required

Recommended Allowedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/io-github-0nork-0nmcp/ai-models.md

WHAT IT DOES

What ai_models does on 0nmcp

AI agents call ai_models to retrieve information from 0nmcp without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

RISK

Why ai_models is rated Low

The primary actions described are listing installed models and getting model info, which are read operations. 'Pull new ones' could be a Write action (downloading/installing a model), but the description emphasizes information retrieval. Since the description is truncated and 'pull' could imply downloading, there's some uncertainty, but overall the blast radius is low as no critical data is modified or deleted.

From the tool's definition List installed, pull new ones, get model info

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs ai_models safely

PolicyLayer is an MCP gateway: it sits between your AI agents and 0nmcp, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For ai_models, this is the rule to start with:

ai_models Allowed

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": {
    "ai_models": {}
  }
}

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

The button opens the PolicyLayer dashboard: create your workspace, connect 0nmcp, apply this rule, and every ai_models call is checked against it from then on.

FAQ

Questions about ai_models

What does the ai_models tool do? +

Manage local AI models. List installed, pull new ones, get model info. Example: ai_models({ action:. It is categorised as a Read tool in the 0nmcp MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on ai_models? +

Register the 0n MCP server in PolicyLayer and add a rule for 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 0nmcp. Nothing to install.

What risk level is ai_models? +

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

Can I rate-limit ai_models? +

Yes. Add a rate_limit block to the 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 ai_models completely? +

Set action: deny in the PolicyLayer policy for 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 ai_models? +

ai_models is provided by the 0n MCP server (0nmcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on 0n, and thousands of servers like it.

This server

All 218 0n tools →

Across the catalogue

The MCP Attack Database →

Guides

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