local_generate · Mcp Ollama MCP: Risk & Policy

WHAT IT DOES

What local_generate does on Mcp Ollama

AI agents invoke local_generate to trigger actions in Mcp Ollama. 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_generate needs a policy

This tool executes inference on a locally-running Ollama model, which constitutes running an external operation (model inference). While it doesn't delete data or move money, it does trigger compute-intensive external processes whose outputs depend on the arguments passed.

From the tool's definition 'General-purpose local LLM generation. Delegates work to a local Ollama model' — triggers external model execution on a local Ollama instance

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

local_generate Rate-limited

local_generate 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_generate": {
      "limits": [
        {
          "counter": "local_generate_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 Mcp Ollama, so you can run agents against it safely.

FAQ

Questions about local_generate

What does the local_generate tool do? +

General-purpose local LLM generation. Delegates work to a local Ollama model to save tokens. Use this when the task is bulk text processing that doesn. It is categorised as a Execute tool in the Mcp Ollama 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_generate? +

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

What risk level is local_generate? +

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

Can I rate-limit local_generate? +

Yes. Add a rate_limit block to the local_generate 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_generate completely? +

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

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