AI agents use conversations_unarchive 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.
Unarchiving a conversation modifies the state of a channel by restoring it from archived status. This is a Write operation because it creates or modifies data reversibly (the archive action can be undone by unarchiving, and unarchiving can be undone by re-archiving). It is not Destructive because the operation is fully reversible and does not irreversibly delete or overwrite data.
From the tool's definition conversations_unarchive: 'Reverse a conversation archive' - this operation restores archived data, which is a reversible modification of Slack workspace state.
Attacks that exploit this kind of access
Reverse a conversation archive. 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 conversations_unarchive: 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_unarchive 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 conversations_unarchive 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_unarchive. 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_unarchive 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 →