AI agents call conversations_members 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 queries and returns member information from a Slack conversation without modifying any data, executing code, or triggering external operations. It is a straightforward read operation on existing conversation metadata. Severity is low because membership lists are typically visible to channel members and pose minimal risk if accessed by an AI agent.
From the tool's definition Tool name 'conversations_members' combined with description 'Retrieve members of a conversation' indicates a data retrieval operation with no modification or deletion capability.
Attacks that exploit this kind of access
Retrieve members of a conversation. 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_members: 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_members 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_members 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_members. 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_members 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 →