conversations_close · Slack MCP: Risk & Policy

WHAT IT DOES

What conversations_close does on Slack

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

WHY IT NEEDS A POLICY

Why conversations_close needs a policy

Closing a conversation is a state-modifying operation that changes channel settings but does not delete data or cause irreversible harm. It falls under Write category as it creates a modified state. Severity is medium because closing a conversation could disrupt communication workflows and affect multiple parties, but the action is typically reversible in Slack (channels/DMs can be reopened).

From the tool's definition Tool name is 'conversations_close' and description states it will 'Close a direct message or multi-party direct message.' The action of closing a conversation modifies the state of a channel/conversation by archiving or closing it, which is reversible…

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

conversations_close Rate-limited

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

FAQ

Questions about conversations_close

What does the conversations_close tool do? +

Close a direct message or multi-party direct message. It is categorised as a Write tool in the Slack MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on conversations_close? +

Register the Slack MCP server in PolicyLayer and add a rule for conversations_close: 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 conversations_close? +

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

Can I rate-limit conversations_close? +

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

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

conversations_close 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.