AI agents use conversations_accept_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.
Accepting a shared invite creates or modifies access permissions and channel membership—a reversible write operation. While not destructive (can be reversed by leaving the channel), it changes organizational state and could grant unintended access to sensitive channels.
From the tool's definition Tool name 'conversations_accept_shared_invite' indicates acceptance of a shared channel invitation, which modifies workspace membership and channel access state. Part of Slack MCP server providing full access to channels and related operations.
Attacks that exploit this kind of access
conversations_accept_shared_invite. 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_accept_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_accept_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_accept_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_accept_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_accept_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 →