ollama_pull · Promethean OS MCP: Risk & Policy

WHAT IT DOES

What ollama_pull does on Promethean OS MCP

AI agents invoke ollama_pull to trigger actions in Promethean OS 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_pull needs a policy

This tool queues a model pull operation, which triggers an external operation (downloading/pulling an AI model). Even though the description notes it's a 'no-op executor in MVP', the intended behavior is to initiate a network/download operation. The 'no-op' qualifier lowers confidence since it may have no real effect currently, but the design intent is to execute an external pull operation.

From the tool's definition Queue a model pull (no-op executor in MVP)

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

ollama_pull Rate-limited

ollama_pull 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_pull": {
      "limits": [
        {
          "counter": "ollama_pull_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 Promethean OS MCP, so you can run agents against it safely.

FAQ

Questions about ollama_pull

What does the ollama_pull tool do? +

Queue a model pull (no-op executor in MVP). It is categorised as a Execute tool in the Promethean OS 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_pull? +

Register the Promethean OS MCP server in PolicyLayer and add a rule for ollama_pull: 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 Promethean OS MCP. Nothing to install.

What risk level is ollama_pull? +

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

Can I rate-limit ollama_pull? +

Yes. Add a rate_limit block to the ollama_pull 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_pull completely? +

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

ollama_pull is provided by the Promethean OS MCP server (octave-commons/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.