ollama_serve · Unified MCP Server MCP: Risk & Policy

WHAT IT DOES

What ollama_serve does on Unified MCP Server

AI agents invoke ollama_serve to trigger actions in Unified MCP Server. 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_serve needs a policy

Starting an Ollama server is an Execute-category action because it triggers an external operation (service startup) whose effects depend on system configuration and potentially on what models/processes the server subsequently runs. While not destructive or financial, it modifies system state and initiates background processes that could consume resources or expose model inference capabilities.

From the tool's definition Tool name 'ollama_serve' with description 'Start Ollama server' indicates launching a service/daemon that initiates external operations and system-level processes.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

ollama_serve Rate-limited

ollama_serve 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_serve": {
      "limits": [
        {
          "counter": "ollama_serve_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 Unified MCP Server, so you can run agents against it safely.

FAQ

Questions about ollama_serve

What does the ollama_serve tool do? +

Start Ollama server. It is categorised as a Execute tool in the Unified MCP Server 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_serve? +

Register the Unified MCP Server MCP server in PolicyLayer and add a rule for ollama_serve: 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 Unified MCP Server. Nothing to install.

What risk level is ollama_serve? +

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

Can I rate-limit ollama_serve? +

Yes. Add a rate_limit block to the ollama_serve 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_serve completely? +

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

ollama_serve is provided by the Unified MCP Server MCP server (qingyunyupan/ollama-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.