AI agents use users_admin_invite 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.
This tool creates a new user account and assigns admin privileges, which is a reversible but consequential data modification. It does not delete data (not Destructive), does not directly move money (not Financial), and does not execute arbitrary code (not Execute). However, granting admin access is a high-severity action because it grants broad permissions that could enable further compromise.
From the tool's definition Tool name contains 'invite' and description states 'Invite a user to the workspace as admin'. This creates a new user account with elevated privileges in the workspace.
Risk signalsAdmin/system-level operation
Attacks that exploit this kind of access
Invite a user to the workspace as admin (legacy undocumented). 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.
Register the Slack MCP server in PolicyLayer and add a rule for users_admin_invite: 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.
users_admin_invite is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the users_admin_invite 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.
Set action: deny in the PolicyLayer policy for users_admin_invite. 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.
users_admin_invite 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.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →