- Home
- MCP servers
- Slack
Slack
- python
2
GitHub Stars
python
Language
4 months ago
First Indexed
2 months ago
Catalog Refreshed
Documentation & install
Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.
Transform your Slack workspace into an autonomous AI-powered assistant with a production-ready Slack MCP Server. It combines real-time Slack Socket Mode interactions with AI-powered tooling to manage the workspace, run web research, and execute cross-tool tasks, all via an extensible MCP framework.
How to use
You run a local MCP server that connects to Slack in real time and exposes a suite of AI tools. Install the server, start it, and then interact with it from Slack by mentioning the bot or directing it through commands. The autonomous AI agent can plan multi-step tasks, discover available tools, perform web research, and deliver results back to Slack channels. Use the multi-tool capabilities to analyze conversations, synthesize insights, and post updates automatically.
How to install
Prerequisites: you need Python 3.11 or newer and a working network connection to Slack, OpenAI, and Tavily APIs. Ensure you have Python installed and you can install dependencies.
Step-by-step commands to set up and run the server locally.
git clone https://github.com/bahakizil/slack_mcp.git
cd slack_mcp
pip install -r requirements.txt
Additional setup and runtime
Configure your environment with API keys and tokens that your MCP server needs to connect to Slack and AI services.
SLACK_BOT_TOKEN=xoxb-your-bot-token
SLACK_APP_TOKEN=xapp-your-app-token
OPENAI_API_KEY=sk-your-openai-key
TAVILY_API_KEY=tvly-your-tavily-key
Start the server
Launch the server using Python. The server will start in real-time Socket Mode and expose an HTTP endpoint for health checks.
python main.py
Cloud integration example
If you want to connect to Claude Desktop, you can add the MCP server configuration to Claude Desktop so it can start the server automatically within that environment.
{
"mcpServers": {
"slack_ai_assistant": {
"command": "python",
"args": ["/full/path/to/main.py"],
"env": {
"SLACK_BOT_TOKEN": "xoxb-your-actual-bot-token-here",
"SLACK_APP_TOKEN": "xapp-your-actual-app-token-here",
"OPENAI_API_KEY": "sk-your-actual-openai-api-key-here",
"TAVILY_API_KEY": "tvly-your-actual-tavily-api-key-here"
}
}
}
}
Available tools
send_slack_message
Send messages to a specified Slack channel
get_slack_channels
List all channels in the workspace
get_slack_messages
Retrieve message history from a channel
search_slack_messages
Search messages across the workspace
create_slack_channel
Create a new Slack channel
analyze_slack_conversation
AI-powered analysis of a Slack conversation
ask_ai
Ask questions to the AI model for explanations or brainstorming
autonomous_assistant
Self-planning AI agent capable of multi-step tasks
search_web
General web search
search_news
News-specific search
research_topic
Deep research analysis on a topic
add_mcp_server
Connect external MCP servers
list_mcp_servers
Show all configured MCP servers
connect_mcp_server
Establish connections to external MCP servers
disconnect_mcp_server
Close connections to external MCP servers
list_external_tools
Browse external MCP tools
call_external_tool
Execute external MCP tools