AI agents use users_set_presence 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.
Setting presence is a write operation that changes user status/state in Slack. While reversible and not destructive, it modifies data. The blast radius is medium because spoofing presence (appearing online/offline when you're not) could be used for social engineering, impersonation, or disrupting team coordination, but the impact is limited to presence status and doesn't directly access sensitive data, delete…
From the tool's definition Tool name is 'users_set_presence' and description states 'Manually set user presence' — this modifies user state (presence status) in Slack, which is a reversible change to user data.
Attacks that exploit this kind of access
Manually set user presence. 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_set_presence: 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_set_presence 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_set_presence 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_set_presence. 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_set_presence 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 →