ollama_run · Unified MCP Server MCP: Risk & Policy

WHAT IT DOES

What ollama_run does on Unified MCP Server

AI agents invoke ollama_run 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_run needs a policy

The tool executes code or model inference operations via Ollama, which can produce arbitrary outputs based on input prompts. While not inherently destructive, execution of untrusted models or prompts could generate malicious code, commands, or data. This qualifies as Execute rather than Read because it triggers external operations with side effects beyond simple data retrieval.

From the tool's definition Tool name 'ollama_run' and description 'Run a model' indicate execution of an external model/process. Combined with sibling tools (code_generate, code_execute context) and Ollama's capability to run arbitrary LLMs, this triggers external operations whose…

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

ollama_run Rate-limited

ollama_run 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_run": {
      "limits": [
        {
          "counter": "ollama_run_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_run

What does the ollama_run tool do? +

Run a model. 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_run? +

Register the Unified MCP Server MCP server in PolicyLayer and add a rule for ollama_run: 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_run? +

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

Can I rate-limit ollama_run? +

Yes. Add a rate_limit block to the ollama_run 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_run completely? +

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

ollama_run 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.