Open or get the DM channel with a user by their Slack User ID. REQUIRES a Slack User ID (U... or W...) — does NOT accept names or usernames. Use lookup_user_by_email (preferred, exact match) or list_slack_users to get the User ID first. Returns the DM channel ID (D...) plus verified recipient ide...
AI agents use open_slack_dm to create or update resources in Apple Shortcuts — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Apple Shortcuts environment.
This tool creates or modifies Slack data by establishing a direct message channel. While it does not send a message itself ("Does NOT send a notification"), it creates the channel infrastructure necessary for subsequent messaging. This is a reversible modification (DM channels can be closed/archived), so it fits the Write category rather than Execute or Destructive.
From the tool's definition Tool description states it will "Open or get the DM channel" and "Returns the DM channel ID" for use with post_slack_message. Opening/creating a DM channel is a write operation that modifies Slack's messaging state.
Documented attack patterns abuse exactly the kind of access open_slack_dm gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Apple Shortcuts, and nothing reaches the server without passing your rules. This is the rule we recommend for open_slack_dm:
{
"version": "1",
"default": "deny",
"tools": {
"open_slack_dm": {
"limits": [
{
"counter": "open_slack_dm_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}open_slack_dm stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Open or get the DM channel with a user by their Slack User ID. REQUIRES a Slack User ID (U... or W...) — does NOT accept names or usernames. Use lookup_user_by_email (preferred, exact match) or list_slack_users to get the User ID first. Returns the DM channel ID (D...) plus verified recipient identity for use with post_slack_message. Does NOT send a notification. WORKFLOW: 1. lookup_user_by_email({ email:. It is categorised as a Write tool in the Apple Shortcuts MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Apple Shortcuts MCP server in PolicyLayer and add a rule for open_slack_dm: 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 Apple Shortcuts. Nothing to install.
open_slack_dm 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 open_slack_dm 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 open_slack_dm. 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.
open_slack_dm is provided by the Apple Shortcuts MCP server (@mindstone/mcp-server-apple-shortcuts). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Apple Shortcuts, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
423 Apple Shortcuts tools catalogued and risk-classified — across an index of 43,000+ MCP servers.