chat_send · Anythingllm MCP: Risk & Policy

WHAT IT DOES

What chat_send does on Anythingllm

AI agents invoke chat_send 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_send needs a policy

Sending a chat message triggers an external operation on the AnythingLLM platform. It may cause the AI to take further actions, invoke tools, or produce stored conversation records. While not purely destructive or financial, the effects depend heavily on arguments and can have downstream consequences, placing it in Execute.

From the tool's definition 'Send chat message' — triggers an external operation (chat interaction with AnythingLLM platform) whose effects depend on the message content and target workspace/thread

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

chat_send Rate-limited

chat_send 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_send": {
      "limits": [
        {
          "counter": "chat_send_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_send

What does the chat_send tool do? +

Send chat message. 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_send? +

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

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

Can I rate-limit chat_send? +

Yes. Add a rate_limit block to the chat_send 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_send completely? +

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

chat_send 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.