AI agents use drafts_create 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.
Creating drafts is a reversible write operation that modifies state (adds new draft objects) without deleting or overwriting existing data. While the description is empty, the tool name and server context make the intent clear. Severity is medium because drafts are typically not immediately visible to others and can be easily deleted, limiting blast radius compared to publishing actual messages.
From the tool's definition Tool name 'drafts_create' indicates creation of draft messages. Server description states it 'Provides LLMs full access to Slack: messages, channels, files, canvases, lists, search, reactions, and more via 220 tools.' The 'create' verb and context of…
Attacks that exploit this kind of access
drafts_create. 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 drafts_create: 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.
drafts_create 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 drafts_create 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 drafts_create. 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.
drafts_create 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 →