Send a single rich embed (title, description, color, fields, author, footer, images, timestamp). Use discord_send_message for plain text, or discord_send_multiple_embeds to send several embeds at once. Requires the Send Messages and Embed Links permissions. Returns the new message ID.
AI agents use discord_send_embed to create or update resources in Discord — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Discord environment.
This tool creates new data (a Discord message) reversibly. The action is Write-class because messages can be deleted or edited after creation, making it non-destructive. Severity is medium rather than low because an agent sending spam, scams, or misleading embeds to many channels could disrupt communities and spread misinformation, though the impact is limited to Discord and reversible.
From the tool's definition Tool sends/creates a new message with embed formatting to Discord. Description explicitly states it 'Send[s] a single rich embed' and 'Returns the new message ID', indicating message creation.
Attacks that exploit this kind of access
Send a single rich embed (title, description, color, fields, author, footer, images, timestamp). Use discord_send_message for plain text, or discord_send_multiple_embeds to send several embeds at once. Requires the Send Messages and Embed Links permissions. Returns the new message ID. It is categorised as a Write tool in the Discord MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Discord MCP server in PolicyLayer and add a rule for discord_send_embed: 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 Discord. Nothing to install.
discord_send_embed 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 discord_send_embed 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 discord_send_embed. 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.
discord_send_embed is provided by the Discord MCP server (@pasympa/discord-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 →