AI agents use users_prefs_set 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 modifies user preferences, which is a reversible write operation. Severity is high because: (1) it can alter user configurations in Slack, affecting productivity and security settings, (2) it targets user-level data rather than message-level, (3) the 'legacy undocumented' nature suggests unclear scope and potential for unintended side effects, and (4) in the context of 220 tools providing 'full access' to…
From the tool's definition Tool name 'users_prefs_set' combined with description 'Set a user preference' clearly indicates a write operation that modifies user settings or preferences.
Attacks that exploit this kind of access
Set a user preference (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_prefs_set: 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_prefs_set 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_prefs_set 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_prefs_set. 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_prefs_set 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 →