AI agents use conversations_approve_shared_invite 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.
This tool creates or modifies shared channel access permissions, which is a reversible write operation. It doesn't read-only data, execute arbitrary code, delete resources, or involve financial transactions.
From the tool's definition Tool name contains 'approve' and description states 'Approve an invitation to a Slack Connect channel', indicating it modifies the state of an invitation from pending to approved, creating a new channel membership or connection.
Attacks that exploit this kind of access
Approve an invitation to a Slack Connect channel. 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_approve_shared_invite: 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_approve_shared_invite 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_approve_shared_invite 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_approve_shared_invite. 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_approve_shared_invite 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 →