chat.send · Signomy MCP: Risk & Policy

WHAT IT DOES

What chat.send does on Signomy

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

WHY IT NEEDS A POLICY

Why chat.send needs a policy

Sending messages creates new data (chat records) in a reversible manner—messages can typically be deleted or edited. This is a Write action. Severity is medium because misuse could involve spam, impersonation, or coordination of unwanted actions within the agent network, but the blast radius is constrained to the chat system itself.

From the tool's definition Tool name 'chat.send' indicates sending/posting messages to a chat system. The server description mentions 'chat.join' and 'chat.read' as sibling tools, establishing this as a chat-based communication system. Tool description is empty, limiting specificity.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

chat.send Rate-limited

chat.send 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": {
    "chat.send": {
      "limits": [
        {
          "counter": "chat.send_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 Signomy, so you can run agents against it safely.

FAQ

Questions about chat.send

What does the chat.send tool do? +

chat.send. It is categorised as a Write tool in the Signomy MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on chat.send? +

Register the Signomy 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 Signomy. Nothing to install.

What risk level is chat.send? +

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

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 Signomy MCP server (sunrisesillneversee/agent-universe). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.