AI agents use slack_lists_access_set to create or update resources in Slack — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Slack environment.
The tool appears to modify access permissions for Slack lists, making it a Write operation (creates or modifies data reversibly). This could affect who can view or interact with lists, making it medium severity—an AI agent could inadvertently grant overly broad access or lock users out, but the change is reversible.
From the tool's definition Tool name 'slack_lists_access_set' indicates modification of access controls for Slack lists. The verb 'set' combined with 'access' suggests changing permissions or sharing settings, which is a reversible write operation.
Attacks that exploit this kind of access
slack_lists_access_set. It is categorised as a Write tool in the Slack MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Slack MCP server in PolicyLayer and add a rule for slack_lists_access_set: 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.
slack_lists_access_set is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the slack_lists_access_set 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_lists_access_set. 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_lists_access_set 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 →