This record as markdown: /tools/karbassi-slack-mcp/calls-end.md
What calls_end does on Slack
AI agents invoke calls_end to trigger actions in Slack. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call: builds kicked off, notifications sent, workflows started.
Why calls_end is rated High
Ending a call is an irreversible action for that call session (you cannot 'un-end' a call), but it doesn't delete data or move money. It triggers an external operation (terminating a live call) whose impact depends on context — could disrupt active meetings. Closest to Execute since it triggers an external operation, though it has a mild destructive flavor. Severity is medium as it can disrupt ongoing communications.
From the tool's definition 'End a call' — terminates an active Slack call session, which is an external operation with real effects on ongoing communications
Attacks that exploit this kind of access
The rule that runs calls_end safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Slack, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For calls_end, this is the rule to start with:
calls_end stays usable, but rate-capped: a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Slack, apply this rule, and every calls_end call is checked against it from then on.
Questions about calls_end
End a call. It is categorised as a Execute tool in the Slack MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Slack MCP server in PolicyLayer and add a rule for calls_end: 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.
calls_end is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the calls_end 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 calls_end. 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.
calls_end 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.
More on Slack, and thousands of servers like it.
Across the catalogue