AI agents use pin_message 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.
Pinning a message modifies channel state by highlighting/organizing a message, making it permanently visible in the channel's pinned list. This is reversible (messages can be unpinned), non-destructive, and has no financial impact. However, it affects channel organization and visibility which is why severity is medium rather than low.
From the tool's definition Tool name 'pin_message' and description 'Pin a message in a channel' indicate a message state modification operation. Pinning is a reversible action that modifies message metadata without deleting or destroying data.
Attacks that exploit this kind of access
Pin a message in a channel. 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 pin_message: 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.
pin_message 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 pin_message 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 pin_message. 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.
pin_message is provided by the Discord MCP server (scarecr0w12/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 →