Connect Slack to Cursor

Read Slack channel messages in Cursor. Connect your workspace, choose an accessible public channel, and retrieve up to five recent messages through OOMOL MCP.

Start Working with Slack

Start Working with Slack

Authorize your Slack user account through OAuth.

Check Resource Access First

A Slack account with access to the workspace and conversations you want to use.

Connect Slack

Sign in to OOMOL, select your team, and create the Slack connection using a supported authorization method. Check that the connection is active, then use the same team in your MCP configuration or oo CLI login.

Connect Slack
  • A Slack account with access to the workspace and conversations you want to use.
  • Choose the permissions needed for your task. Message search, conversation history, and sending messages require their respective permissions.
Choose Your Access Method

For clients that support remote HTTP MCP and custom authentication headers.

  1. Open the MCP setup page, sign in, and select the team containing your application connection. Use Copy MCP Configuration to get the key and headers.
  2. Add the configuration using the MCP client instructions below, then reconnect your client.
  3. Copy the read-only verification task into your AI chat and run it.
Configure MCP MCP Client Configuration →

For agents that can run terminal commands and use the oo Skill.

  1. Follow the agent setup page to install oo CLI and the oo Skill.
  2. Sign in to the OOMOL team containing your application connection. Use oo login --team <team-name> with your team name.
  3. Copy the read-only verification task into your agent chat and run it.
Set Up oo CLI + Skill CLI Installation Guide →

MCP Client Configuration

Get MCP Configuration

Replace the placeholders with the key and team name from the OOMOL setup page. Keep credentials private and preserve other server entries.

Cursor

Open ~/.cursor/mcp.json in your home folder. If it does not exist, create it with the JSON copied from OOMOL. Otherwise, merge the oomol entry into the existing mcpServers object. Save, reconnect the server, and start a new agent chat.

{
  "mcpServers": {
    "oomol": {
      "url": "https://connector.oomol.com/v1/mcp",
      "headers": {
        "Authorization": "Bearer <mcp-api-key>",
        "x-oo-team-name": "<team-name>"
      }
    }
  }
}
Verify the Connection
  1. Enable oomol in Cursor’s MCP settings and confirm that its tools load without an authentication error. Start a new Agent chat with the server enabled.
  2. Run the read-only verification task in a new AI chat to check access to your resource and its data.

Look for OOMOL tools such as connector_list_apps and connector_search_actions. They discover and run Slack actions; each action may not appear as a separate MCP tool. Frequently Asked Questions →

Verify Your First Slack Query

Copy this read-only task into a new AI chat. If it fails, check the FAQ.

Choose Your Access Method

Verify Your First Slack Query

Check that the returned resource identifier matches your target and review the query results.

Use OOMOL MCP only. Check that Slack has an active user-account connection in the configured OOMOL team. List at most 5 visible public channels and ask me to choose a target. Read at most 5 recent messages from that channel. Return the channel ID, message timestamps, and text actually returned. Report empty history and permission errors separately. Do not post, reply, react, join channels, or change anything.

Frequently Asked Questions

Why can I connect but not read my resource?
Use the OOMOL team containing your active application connection. Application authorization, the MCP key, and resource permissions are separate checks. Inspect the tool error and confirm the resource ID and query range. Report empty results separately from access errors; keep keys private. For Slack, check the authorized user account and workspace. The initial channel list covers visible public channels. Reading history requires the relevant conversation access and history permission. A successful channel listing does not prove history access; private channels and thread replies need separate checks.
Does this connection post as me or as a bot?
It uses Slack user OAuth authorization. Messages are sent as the connected user; a separate bot connection is a different integration.
Can AI read private channels and direct messages?
Access depends on the connected user and granted conversation permissions. Connecting Slack does not grant access to every conversation in the workspace.
Can a summary include links to the original messages?
Yes. Ask the assistant to include source links. Search results can include message links, and a separate operation retrieves a permalink for a specified channel and message.
Can I review an update before it is sent?
Ask the assistant to prepare the text in your conversation for review. This integration has message posting and reply operations, but no Slack draft-saving operation.