Skip to content

phuc-nt/slack-browser-mcp-server

Repository files navigation

Slack MCP Server

AI meets Slack - Connect AI assistants to your Slack workspace with interactive messaging support

Tools Block Kit License Status

🚀 What is this?

Slack MCP Server enables AI assistants like Claude, Cline, Cursor, and other MCP-compatible tools to interact with Slack workspaces using browser tokens - featuring Block Kit interactive messaging, advanced search capabilities, and enterprise-ready architecture. No app installation or admin approval needed.

✨ Features

🔧 12 Production Tools:

  • Interactive Messaging (6): post_message, update_message, delete_message, react_to_message, post_message_blocks, update_message_blocks
  • Data Retrieval (4): get_thread_replies, list_workspace_channels, list_workspace_users, get_user_profile
  • Advanced Search (2): search_messages (50+ query patterns + AI workflows), search_files (with custom query support for flexible thread collection)

🎯 Key Capabilities:

  • Browser Token Authentication - No app installation or admin approval needed
  • Block Kit Interactive Messaging - Rich content with buttons, forms, dashboards, and workflows
  • Advanced Search - 50+ comprehensive query patterns, AI-optimized synthesis workflows, flexible thread collection

🚀 Quick Start

📦 Install from NPM (Recommended)

npm install -g slack-browser-mcp-server

📖 Complete Installation Guide - Follow the step-by-step setup guide

💡 Usage Examples

Progress Summary & Block Kit Report:

Human: Summarize the progress from the last 3 days in the "engineering" channel, write a Block Kit report, and send it to "manager"

AI Assistant: I'll help you create a progress summary report. Here's my plan:
□ Use search_messages to find recent updates in #engineering channel
□ Use get_thread_replies to get detailed context from important discussions
□ Use get_user_profile to get manager's user ID
□ Use post_message_blocks to create and send a structured Block Kit report

Thread Analysis & Response Guidance:

Human: Summarize thread "1754405258.272689" and tell me how I should respond

AI Assistant: I'll analyze this thread and provide response guidance:
□ Use get_thread_replies to retrieve all messages in the thread
□ Review participants, timeline, and key discussion points
□ Analyze conversation context and sentiment
□ Provide summary and suggest appropriate response options

Topic Discovery & Information Synthesis:

Human: Find where people are discussing "deployment issues" and provide a comprehensive summary

AI Assistant: I'll search and synthesize deployment discussions across your workspace:
□ Use search_messages to find "deployment issues" across all channels
□ Use get_thread_replies to get full context from relevant threads
□ Use list_workspace_channels to identify which teams are involved
□ Compile comprehensive summary with key issues, solutions, and participants

🛠️ Tech Stack

  • TypeScript - Type-safe development with strict mode
  • Node.js - Runtime environment (16.x+)
  • MCP Protocol - Model Context Protocol for AI integration
  • Slack APIs - Native Slack Web API integration
  • Block Kit - Interactive messaging framework

📄 License

MIT License - see LICENSE for details.


🎉 Connect your AI assistant to Slack with full interactive messaging support!

About

No description, website, or topics provided.

Resources

License

Stars

Watchers

Forks

Packages

No packages published