chat_with_local_model

THE RISK

High Risk

Why chat_with_local_model needs a policy

This tool executes a chat interaction with a local AI model via Ollama, triggering external computation whose effects depend on the prompt arguments. The model's response may include tool use, code execution, or other side effects depending on the model's capabilities and system prompt.

From the tool's definition Chat with a Local AI (Ollama) model

Documented attack patterns abuse exactly the kind of access chat_with_local_model gives an agent:

POLICY

How to control chat_with_local_model

PolicyLayer is an MCP gateway — it sits between your AI agents and Msty Admin MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for chat_with_local_model:

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "chat_with_local_model": {
      "limits": [
        {
          "counter": "chat_with_local_model_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

chat_with_local_model 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.

Create a free account and register Msty Admin MCP — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

RATE-LIMIT THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More Msty Admin MCP tools

Execute bloom_evaluate_model Run Bloom behavioral evaluation on a model. Execute run_calibration_test Run calibration test on a model. Execute chat_with_llamacpp_model Chat with a LLaMA.cpp model. Execute chat_with_mlx_model Chat with an MLX model. Write sync_claude_preferences Sync Claude preferences with Msty. Write generate_persona Generate AI persona configuration. Write import_tool_config Import tool configuration. Read identify_handoff_triggers Identify handoff trigger patterns.

All 36 Msty Admin MCP tools →

Execute tools on other servers

Android Forensics ADB MCP Server adb_shell_command EMBA-MCP run_emba_scan Frida Game Hacking MCP remove_breakpoint Procmon request_elevation

Go deeper

High-risk tools in Msty Admin MCP → Every high-risk tool this server exposes, in one view.
All high-risk MCP tools → Every high-risk tool across the catalogue, and the policy pattern that contains them.
The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Agent sandbox → Bounding what an agent can execute and where the boundary should sit.
Least privilege for MCP → Granting agents the minimum tool surface the task needs.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about chat_with_local_model

What does the chat_with_local_model tool do? +

Chat with a Local AI (Ollama) model. It is categorised as a Execute tool in the Msty Admin 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 chat_with_local_model? +

Register the Msty Admin MCP server in PolicyLayer and add a rule for chat_with_local_model: 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 Msty Admin MCP. Nothing to install.

What risk level is chat_with_local_model? +

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

Can I rate-limit chat_with_local_model? +

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

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

chat_with_local_model is provided by the Msty Admin MCP server (m-pineapple/msty-admin-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Msty Admin MCP tool call.

Start from Msty Admin MCP, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →