Slack MCP Server

Provides access to the Slack API through the Model Context Protocol. Enables AI agents to read and send messages, manage channels, search conversation history, and interact with Slack workspaces. Supports listing channels, reading threads, posting messages, and adding reactions programmatically. Originally maintained by Anthropic, now maintained by Zencoder.

{
  "mcpServers": {
    "slack": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-slack"
      ],
      "env": {
        "SLACK_BOT_TOKEN": "<YOUR_SLACK_BOT_TOKEN>",
        "SLACK_TEAM_ID": "<YOUR_SLACK_TEAM_ID>"
      }
    }
  }
}

{
  "type": "object",
  "required": [
    "channel_id",
    "text"
  ],
  "properties": {
    "text": {
      "type": "string",
      "description": "Message text to send (supports Slack markdown)"
    },
    "thread_ts": {
      "type": "string",
      "description": "Thread timestamp to reply in a thread"
    },
    "channel_id": {
      "type": "string",
      "description": "Slack channel or conversation ID"
    }
  }
}

{
  "type": "object",
  "properties": {
    "limit": {
      "type": "integer",
      "description": "Maximum number of channels to return (default 100)"
    },
    "cursor": {
      "type": "string",
      "description": "Pagination cursor for next page of results"
    }
  }
}

{
  "type": "object",
  "required": [
    "channel_id"
  ],
  "properties": {
    "limit": {
      "type": "integer",
      "description": "Number of messages to retrieve (default 10)"
    },
    "channel_id": {
      "type": "string",
      "description": "Slack channel ID"
    }
  }
}

{
  "type": "object",
  "required": [
    "query"
  ],
  "properties": {
    "count": {
      "type": "integer",
      "description": "Number of results to return"
    },
    "query": {
      "type": "string",
      "description": "Search query string"
    }
  }
}

{
  "type": "object",
  "required": [
    "channel_id",
    "timestamp",
    "reaction"
  ],
  "properties": {
    "reaction": {
      "type": "string",
      "description": "Emoji name without colons (e.g., thumbsup)"
    },
    "timestamp": {
      "type": "string",
      "description": "Timestamp of the message to react to"
    },
    "channel_id": {
      "type": "string",
      "description": "Channel containing the message"
    }
  }
}