AI agents call users_prefs_get to retrieve information from Slack without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves user preferences without modifying or deleting data. However, user preferences may contain sensitive personal configuration data (notification settings, display preferences, etc.), warranting medium severity due to potential privacy exposure if misused by an AI agent to extract user-specific information from multiple accounts.
From the tool's definition Tool name 'users_prefs_get' and description 'Get user preferences' indicate data retrieval with no modification. The term 'get' is explicitly a Read operation per the classification rules.
Attacks that exploit this kind of access
Get user preferences (legacy undocumented). It is categorised as a Read tool in the Slack MCP Server, which means it retrieves data without modifying state.
Register the Slack MCP server in PolicyLayer and add a rule for users_prefs_get: 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_get is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the users_prefs_get 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_get. 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_get 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 →