openai_chat_completion · Anythingllm MCP: Risk & Policy

WHAT IT DOES

What openai_chat_completion does on Anythingllm

AI agents invoke openai_chat_completion to trigger actions in Anythingllm. 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 openai_chat_completion needs a policy

This tool executes an external operation (calling the OpenAI API for chat completion), which may incur costs and involve processing arbitrary input. The description is minimal, lowering confidence slightly, but the name strongly implies an outbound API call.

From the tool's definition Tool name 'openai_chat_completion' and description 'Chat completion' — triggers an external API call to OpenAI to generate a chat completion response.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

openai_chat_completion Rate-limited

openai_chat_completion 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": {
    "openai_chat_completion": {
      "limits": [
        {
          "counter": "openai_chat_completion_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 Anythingllm, so you can run agents against it safely.

FAQ

Questions about openai_chat_completion

What does the openai_chat_completion tool do? +

Chat completion. It is categorised as a Execute tool in the Anythingllm MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on openai_chat_completion? +

Register the Anythingllm MCP server in PolicyLayer and add a rule for openai_chat_completion: 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 Anythingllm. Nothing to install.

What risk level is openai_chat_completion? +

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

Can I rate-limit openai_chat_completion? +

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

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

openai_chat_completion is provided by the Anythingllm MCP server (moliver28/anythingllm-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.