Slack / Community
Slack MCP Server
MCP server that connects AI coding agents to Slack workspaces for reading channel context, searching messages, and posting updates during development workflows.
Last reviewed Feb 26, 2026
What it does
The Slack MCP Server gives AI coding agents access to your Slack workspace. Agents can search message history for context on past decisions, read channel discussions about requirements, and post status updates when work is complete. This is useful for teams where important context lives in Slack threads rather than formal documentation.
Available tools
| Tool | What it does |
|---|---|
slack_list_channels |
List public and joined channels in the workspace |
slack_post_message |
Send a message to a channel or thread |
slack_reply_to_thread |
Reply to a specific message thread |
slack_get_channel_history |
Read recent messages from a channel |
slack_get_thread_replies |
Get all replies in a message thread |
slack_search_messages |
Search messages across the workspace |
slack_get_users |
List workspace members |
slack_get_user_profile |
Get profile details for a specific user |
Setup by tool
Cursor
Create .cursor/mcp.json in your project root:
{
"mcpServers": {
"slack": {
"command": "npx",
"args": ["-y", "@modelcontextprotocol/server-slack"],
"env": {
"SLACK_BOT_TOKEN": "xoxb-your-bot-token",
"SLACK_TEAM_ID": "T01234ABCDE"
}
}
}
}
Claude Code
Add to your Claude configuration file:
{
"mcpServers": {
"slack": {
"command": "npx",
"args": ["-y", "@modelcontextprotocol/server-slack"],
"env": {
"SLACK_BOT_TOKEN": "xoxb-your-bot-token",
"SLACK_TEAM_ID": "T01234ABCDE"
}
}
}
}
Creating a Slack bot token
- Go to api.slack.com/apps and create a new app
- Under OAuth & Permissions, add these bot token scopes:
channels:history,channels:read,chat:write,search:read,users:read - Install the app to your workspace and copy the Bot User OAuth Token (starts with
xoxb-) - Find your team ID in the workspace URL or Slack admin settings
When to use this
- Context recovery: Search for past discussions about a feature before reimplementing it
- Requirements clarification: Read the channel where a feature was discussed to understand intent
- Deployment notifications: Post automated messages when agents complete significant work
- Cross-team coordination: Read messages from other team channels for dependency context
Security considerations
- Use the minimum required OAuth scopes for your workflow
- Bot tokens can access all channels they're invited to; be selective about channel membership
- Avoid using
chat:writescope if agents only need to read context - Message search may surface sensitive information; consider scope limitations
- Store bot tokens in environment variables, not in committed files
Compatibility
Related MCP servers
Documentation MCP Server
MCP server pattern for giving AI coding agents direct access to versioned documentation, internal playbooks, and API references to reduce hallucinated guidance.
Filesystem MCP Server
Reference MCP server that grants AI coding agents controlled read/write access to local files and directories within sandboxed project boundaries.
GitHub MCP Server
Official MCP server that connects AI coding agents to GitHub repositories, pull requests, issues, and code search through the Model Context Protocol.