AI agents call slack_users to retrieve information from Access without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a read-only operation that queries and retrieves Slack workspace membership data. While it does expose potentially sensitive information (email addresses, user identifiers, online status) that could be misused for social engineering or reconnaissance, the tool itself performs no write, execute, or destructive actions.
From the tool's definition Tool description states 'List all members' and 'look up user IDs' — purely retrieval operations with no modification, deletion, or execution. The data returned (user IDs, display names, emails, online status) is informational.
Attacks that exploit this kind of access
List all members of the Slack workspace with their user IDs, display names, emails, and online status. Use this to look up user IDs or find team members. It is categorised as a Read tool in the Access MCP Server, which means it retrieves data without modifying state.
Register the Access MCP server in PolicyLayer and add a rule for slack_users: 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 Access. Nothing to install.
slack_users 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 slack_users 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 slack_users. 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.
slack_users is provided by the Access MCP server (scottpedia0/access). 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 →