End a Discord poll early and get the final results. Use this when the user has finished voting and wants to submit.
AI agents use end_poll to create or update resources in Cursor Discord Channels — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Cursor Discord Channels environment.
Ending a poll early is a reversible modification to a Discord object (changing its state from active to ended). It does not delete data permanently, execute code, or move money. It does modify the poll's state irreversibly in the sense that a poll can't be un-ended, but this is more akin to a state change/write than a destructive deletion.
From the tool's definition End a Discord poll early and get the final results
Attacks that exploit this kind of access
End a Discord poll early and get the final results. Use this when the user has finished voting and wants to submit. It is categorised as a Write tool in the Cursor Discord Channels MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Cursor Discord Channels MCP server in PolicyLayer and add a rule for end_poll: 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 Cursor Discord Channels. Nothing to install.
end_poll 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 end_poll 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 end_poll. 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.
end_poll is provided by the Cursor Discord Channels MCP server (lilyzhng/cursor-discord-channels). 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 →