local_llm_chat · Ollama MCP Server MCP: Risk & Policy

WHAT IT DOES

What local_llm_chat does on Ollama MCP Server

AI agents invoke local_llm_chat to trigger actions in Ollama 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 local_llm_chat needs a policy

Chatting with a local LLM involves sending prompts to and receiving responses from a running model process. This is an external operation whose effects depend on the arguments supplied (the prompt content and model chosen). It is not a simple read (it actively runs inference), nor write (no persistent data is created), making Execute the most appropriate category.

From the tool's definition Chat with a local Ollama model — triggers execution of a local LLM inference process with arbitrary user-supplied input

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

local_llm_chat Rate-limited

local_llm_chat 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": {
    "local_llm_chat": {
      "limits": [
        {
          "counter": "local_llm_chat_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 Ollama MCP Server, so you can run agents against it safely.

FAQ

Questions about local_llm_chat

What does the local_llm_chat tool do? +

Chat with a local Ollama model. It is categorised as a Execute tool in the Ollama 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 local_llm_chat? +

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

What risk level is local_llm_chat? +

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

Can I rate-limit local_llm_chat? +

Yes. Add a rate_limit block to the local_llm_chat 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 local_llm_chat completely? +

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

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