chat_with_llm · Session Buddy MCP: Risk & Policy

WHAT IT DOES

What chat_with_llm does on Session Buddy

AI agents invoke chat_with_llm to trigger actions in Session Buddy. 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 chat_with_llm needs a policy

This tool makes outbound calls to an external LLM provider, which constitutes executing an external operation. The effects are argument-dependent (the prompt/conversation content determines what the LLM does or returns). It could be used to exfiltrate data, generate harmful content, or incur API costs, giving it a high blast radius if misused by an AI agent.

From the tool's definition 'Have a conversation with an LLM provider' — triggers an external operation (LLM API call) whose effects depend on the arguments passed

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

chat_with_llm Rate-limited

chat_with_llm 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": {
    "chat_with_llm": {
      "limits": [
        {
          "counter": "chat_with_llm_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 Session Buddy, so you can run agents against it safely.

FAQ

Questions about chat_with_llm

What does the chat_with_llm tool do? +

Have a conversation with an LLM provider. It is categorised as a Execute tool in the Session Buddy 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_llm? +

Register the Session Buddy MCP server in PolicyLayer and add a rule for chat_with_llm: 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 Session Buddy. Nothing to install.

What risk level is chat_with_llm? +

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

Can I rate-limit chat_with_llm? +

Yes. Add a rate_limit block to the chat_with_llm 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_llm completely? +

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

chat_with_llm is provided by the Session Buddy MCP server (lesleslie/session-buddy). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.