AI agents call conversations_list_prefs 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 notification and mute preferences for channels, which is a data query operation with no side effects. It does not create, modify, delete, or execute any operations—it only reads existing preference settings. Severity is low because exposure of user notification preferences poses minimal direct risk, though it may reveal user behavior patterns.
From the tool's definition Tool name 'conversations_list_prefs' and description 'Get per-channel notification and mute prefs' indicate retrieval of user preference data without modification. The verb 'Get' and action 'list' confirm read-only behavior.
Attacks that exploit this kind of access
Get per-channel notification and mute prefs (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 conversations_list_prefs: 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.
conversations_list_prefs 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 conversations_list_prefs 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 conversations_list_prefs. 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.
conversations_list_prefs 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 →