conversations_invite_shared · Slack MCP: Risk & Policy

WHAT IT DOES

What conversations_invite_shared does on Slack

AI agents use conversations_invite_shared 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_invite_shared needs a policy

The 'invite' action creates or modifies membership relationships within Slack conversations, which is a reversible write operation. While it doesn't delete data, it does alter permissions and access control. The high severity reflects that an AI agent could be tricked into inviting unauthorized users to sensitive channels or invite spam, affecting organizational security and data access boundaries.

From the tool's definition Tool name 'conversations_invite_shared' indicates inviting users to a shared conversation/channel. Based on sibling tools in the slack-mcp server like 'conversations_*' patterns and the invite action, this modifies channel membership state.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

conversations_invite_shared Rate-limited

conversations_invite_shared 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_invite_shared": {
      "limits": [
        {
          "counter": "conversations_invite_shared_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_invite_shared

What does the conversations_invite_shared tool do? +

conversations_invite_shared. 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_invite_shared? +

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

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

Can I rate-limit conversations_invite_shared? +

Yes. Add a rate_limit block to the conversations_invite_shared 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_invite_shared completely? +

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

conversations_invite_shared 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.