ollama_chat_completion · Unified MCP Server MCP

WHAT IT DOES

What ollama_chat_completion does on Unified MCP Server

AI agents invoke ollama_chat_completion 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_chat_completion needs a policy

Chat completion invokes an LLM to generate responses based on input messages. This is an external operation whose effects depend on the arguments passed (the conversation content and model chosen). It is not a simple read of stored data; it executes a model inference process. Given the server also hosts code generation, analysis, and debugging tools, misuse could produce harmful code or content.

From the tool's definition 'chat completion API' — triggers inference on a local LLM via Ollama, executing model computation with arbitrary user-supplied messages

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

ollama_chat_completion Rate-limited

ollama_chat_completion 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_chat_completion": {
      "limits": [
        {
          "counter": "ollama_chat_completion_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_chat_completion

What does the ollama_chat_completion tool do? +

OpenAI-compatible chat completion API. 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_chat_completion? +

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

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

Can I rate-limit ollama_chat_completion? +

Yes. Add a rate_limit block to the ollama_chat_completion 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_chat_completion completely? +

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

ollama_chat_completion 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.