ollama_start_conversation · Promethean OS MCP: Risk & Policy

WHAT IT DOES

What ollama_start_conversation does on Promethean OS MCP

AI agents invoke ollama_start_conversation 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_start_conversation needs a policy

Although this tool does not destructively delete data or move money, it executes operations external to data read/write—it triggers ollama inference processes. The tool's effect (conversation initiation and message processing) depends on provided arguments and causes external state changes in the ollama runtime.

From the tool's definition The tool name 'ollama_start_conversation' and description 'Create a conversation; optionally seeds initial user message' indicate it initiates a new conversation session.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

ollama_start_conversation Rate-limited

ollama_start_conversation 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_start_conversation": {
      "limits": [
        {
          "counter": "ollama_start_conversation_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_start_conversation

What does the ollama_start_conversation tool do? +

Create a conversation; optionally seeds initial user message. 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_start_conversation? +

Register the Promethean OS MCP server in PolicyLayer and add a rule for ollama_start_conversation: 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_start_conversation? +

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

Can I rate-limit ollama_start_conversation? +

Yes. Add a rate_limit block to the ollama_start_conversation 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_start_conversation completely? +

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

ollama_start_conversation 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.