rtm_connect · Slack MCP: Risk & Policy

WHAT IT DOES

What rtm_connect does on Slack

AI agents invoke rtm_connect to trigger actions in Slack. 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 rtm_connect needs a policy

Starting an RTM session is an active operation that opens a persistent connection to Slack's real-time infrastructure. It does not merely read data or write a record, but executes an ongoing session that can receive and potentially send events. This is an Execute-category action with medium severity, as a misused RTM session could enable covert monitoring or message interception.

From the tool's definition "Start a Real Time Messaging session" — initiates a persistent WebSocket/RTM connection, triggering an external real-time operation

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

rtm_connect Rate-limited

rtm_connect 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": {
    "rtm_connect": {
      "limits": [
        {
          "counter": "rtm_connect_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 Slack, so you can run agents against it safely.

FAQ

Questions about rtm_connect

What does the rtm_connect tool do? +

Start a Real Time Messaging session. It is categorised as a Execute tool in the Slack MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on rtm_connect? +

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

What risk level is rtm_connect? +

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

Can I rate-limit rtm_connect? +

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

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

rtm_connect is provided by the Slack MCP server (karbassi/slack-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.