chat_stream · Anythingllm MCP: Risk & Policy

WHAT IT DOES

What chat_stream does on Anythingllm

AI agents invoke chat_stream 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 chat_stream needs a policy

Streaming chat triggers external AI model execution and platform operations. While it doesn't destructively modify data, it executes live queries against LLM backends and may consume resources or expose sensitive document content from workspaces. The description is minimal, so confidence is moderate.

From the tool's definition 'Stream chat' - triggers real-time streaming of chat interactions with the AnythingLLM platform, invoking external LLM operations

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

chat_stream Rate-limited

chat_stream 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_stream": {
      "limits": [
        {
          "counter": "chat_stream_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 chat_stream

What does the chat_stream tool do? +

Stream chat. 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 chat_stream? +

Register the Anythingllm MCP server in PolicyLayer and add a rule for chat_stream: 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 chat_stream? +

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

Can I rate-limit chat_stream? +

Yes. Add a rate_limit block to the chat_stream 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_stream completely? +

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

chat_stream 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.