ollama_deploy · ML Lab MCP: Risk & Policy

WHAT IT DOES

What ollama_deploy does on ML Lab MCP

AI agents invoke ollama_deploy to trigger actions in ML Lab MCP. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why ollama_deploy needs a policy

This tool executes a deployment operation that activates external infrastructure and model serving. While not destructive (deployment is reversible via undeployment), it goes beyond data creation/modification by triggering operational changes to a live service. The effects depend on arguments (which model, which Ollama instance), and an AI agent could inadvertently deploy malicious or resource-intensive models.

From the tool's definition Tool performs 'Deploy a GGUF model to Ollama' — deploys machine learning models to a runtime environment, which triggers external operations with effects dependent on which model is deployed and the target environment configuration.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

ollama_deploy Rate-limited

ollama_deploy stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "ollama_deploy": {
      "limits": [
        {
          "counter": "ollama_deploy_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches ML Lab MCP, so you can run agents against it safely.

FAQ

Questions about ollama_deploy

What does the ollama_deploy tool do? +

Deploy a GGUF model to Ollama. It is categorised as a Execute tool in the ML Lab MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on ollama_deploy? +

Register the ML Lab MCP server in PolicyLayer and add a rule for ollama_deploy: 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 ML Lab MCP. Nothing to install.

What risk level is ollama_deploy? +

ollama_deploy is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit ollama_deploy? +

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

Set action: deny in the PolicyLayer policy for ollama_deploy. 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 ollama_deploy? +

ollama_deploy is provided by the ML Lab MCP server (pushpullcommitpush/ml-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.