Connect Slack to AI agents over MCP (with Stepper Skill Sets)

Let your AI agent post messages, send DMs and manage channels in Slack through a Stepper Skill Set, limited to the actions you choose.

A Skill Set is a toolkit you build in Stepper: you connect your apps, pick which actions an agent may call, and Stepper serves them as one MCP endpoint. The agent never sees your Slack password or API keys, and every call is logged.

Last checked:

What you can let an agent do in Slack

These are the Slack actions you can add to a Skill Set. They're the same actions Stepper workflows use, listed on Stepper's Slack page. You choose which ones the agent gets.

For example, you could ask

  • Post a summary of today's orders in #shop-updates.
  • Create a channel called #spring-workshop and invite Priya and Sam.
  • Send Channel Message Posts a message to the specific #channel you choose
  • Send Direct Message Sends a direct message to a user or yourself
  • Set Status Sets your Slack status to the given text and emoji
  • Update Profile Update basic profile fields such as name or title
  • Create Channel Creates a new channel
  • Invite User to Channel Invite an existing User to an existing Channel
  • Delete Message Deletes a message from a channel

Set it up in 5 steps

You need a Stepper account, a Slack account, and an AI client that supports remote MCP servers, such as ChatGPT, Claude, Cursor or VS Code. Your own agent works too, using a Skill Set token.

  1. Connect Slack to Stepper

    In Stepper, connect your Slack account. Use an account that can do what you want the agent to do, and no more.

  2. Create a Skill Set

    Go to Skill Sets in Stepper, create a Skill Set for this agent, and use Add Entry to add your Slack connection.

  3. Restrict the actions

    Choose only the Slack actions the agent needs. An entry with no actions chosen allows every Slack action, so a short list is safer. To pin a value, such as one channel, table or calendar, hardcode that parameter so the agent can't change it.

  4. Add the Skill Sets server to your AI client

    Add this URL as a remote MCP server:

    https://mcp.stepper.io/skill-sets/mcp

    Then sign in to Stepper when your client asks. On the Stepper screen that follows, pick the Skill Set this agent should use. To switch to a different Skill Set later, remove the server and connect again.

    Chat apps (ChatGPT, Claude and others): add it as a custom connector or app, wherever your client lists remote MCP servers.

    Code editors (Cursor, Windsurf and others that use an mcpServers config):

    {
  "mcpServers": {
    "stepper": {
      "url": "https://mcp.stepper.io/skill-sets/mcp"
    }
  }
}

    Your own agent or script: generate a Skill Set token in Stepper and send it as Authorization: Bearer sst_….

  5. Test it

    Ask the agent what it can do (it checks the Skill Set's list of skills) and make sure only the Slack actions you chose appear. Then run one request using the lowest-risk action you allowed, such as a lookup or a draft, and check the call in the Skill Set's call log in Stepper.

Slack's own MCP server, and when to use it instead

Slack hosts its own MCP server. MCP clients can use it to search channels and send messages, and workspace admins approve each client that connects. Read Slack's MCP server for setup.

Use Slack's server when the agent needs to search and read conversations. The Skill Set actions above post and manage; they don't read message history.

A Skill Set fits when the agent needs Slack alongside other apps through one endpoint, or when you want to choose exactly which actions it can call, lock parameter values, and check a log of every call.

Guardrails

An agent can misread a request, and some Slack actions change or remove real data. Set these up before you rely on it.

Scope

Allow Send Channel Message but lock the channel to #shop-updates, so the agent can't post anywhere else. Leave Delete Message off.

Use a separate Skill Set for each agent or role, so each one gets only its own actions and tokens.

Audit

Every skill call is logged with the tool name, status, how it authenticated, and when. Call logs are kept for 30 days and are visible in Stepper, so you can check what the agent did in Slack.

Revoke

Revoke a Skill Set token from Stepper to cut off a script or client straight away. To stop an agent using one action, remove it from the Skill Set; that applies from the agent's next call, with no need to reconnect. You can also remove the server from your AI client.

Add with care: Delete Message.

Related

Connect other apps to AI agents over MCP:

Slack is a trademark of its owner. Stepper isn't affiliated with or endorsed by Slack; its name is used here only to describe the integration.