AI agents call search_modules_channels 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 information about channels matching given criteria. It does not create, modify, delete, or execute any actions — it only returns matching results. The 'undocumented session endpoint' notation indicates it accesses Slack's internal API but does not change the nature of the read-only operation. Severity is low because channel name/topic enumeration poses minimal risk even if misused by an AI agent.
From the tool's definition Tool name contains 'search' and description states 'Search channels by name or topic' — a query operation with no side effects.
Attacks that exploit this kind of access
Search channels by name or topic (undocumented session endpoint). 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 search_modules_channels: 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.
search_modules_channels 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 search_modules_channels 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 search_modules_channels. 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.
search_modules_channels 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 →