configure_llm_provider · Session Buddy MCP: Risk & Policy

WHAT IT DOES

What configure_llm_provider does on Session Buddy

AI agents use configure_llm_provider to create or update resources in Session Buddy — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Session Buddy environment.

WHY IT NEEDS A POLICY

Why configure_llm_provider needs a policy

This tool modifies configuration data by storing API credentials and settings for LLM providers. While not destructive (changes are reversible), it creates or updates sensitive configuration. The high severity reflects that misconfiguration or credential injection could compromise API security, enable token theft, or redirect API calls to attacker-controlled endpoints.

From the tool's definition Tool name 'configure_llm_provider' and description 'Configure an LLM provider with API credentials and settings' indicate creation or modification of LLM provider configuration data, including sensitive credentials.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

configure_llm_provider Rate-limited

configure_llm_provider stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "configure_llm_provider": {
      "limits": [
        {
          "counter": "configure_llm_provider_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

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 configure_llm_provider

What does the configure_llm_provider tool do? +

Configure an LLM provider with API credentials and settings. It is categorised as a Write tool in the Session Buddy MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on configure_llm_provider? +

Register the Session Buddy MCP server in PolicyLayer and add a rule for configure_llm_provider: 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 configure_llm_provider? +

configure_llm_provider is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit configure_llm_provider? +

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

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

configure_llm_provider 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.