Post a message to a Slack channel as yourself. DM SAFETY: For direct messages (D... channels), this tool verifies the recipient identity before sending. Always provide intended_recipient (User ID) for DMs to enable mismatch detection. The message is NOT sent if intended_recipient does not match t...
AI agents use post_slack_message 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 new data (Slack messages) in a reversible manner—messages can be edited or deleted post-send. While it can reach many recipients and potentially spread misinformation if misused by an agent, it does not execute arbitrary code, delete data irreversibly, or move money. The DM safety mechanism (recipient verification) mitigates some risks but does not change the core classification.
From the tool's definition Tool description states 'Post a message to a Slack channel as yourself,' which creates new message data in Slack. The parameters (channel, text, intended_recipient) are used to compose and send a message.
Documented attack patterns abuse exactly the kind of access post_slack_message 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 post_slack_message:
{
"version": "1",
"default": "deny",
"tools": {
"post_slack_message": {
"limits": [
{
"counter": "post_slack_message_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}post_slack_message 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.
Post a message to a Slack channel as yourself. DM SAFETY: For direct messages (D... channels), this tool verifies the recipient identity before sending. Always provide intended_recipient (User ID) for DMs to enable mismatch detection. The message is NOT sent if intended_recipient does not match the actual DM recipient. PARAMETERS: channel, text, intended_recipient. Do not use channel_id or message — these are not the parameter names. Posted as the user — messages are editable in Slack. 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 post_slack_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 Apple Shortcuts. Nothing to install.
post_slack_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 post_slack_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 post_slack_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.
post_slack_message 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.