agentic-slackbot

by john-lin

MCP Client 5 stars
  • agent-framework

An agentic Slack bot with MCP support.

About

What is agentic-slackbot?

A simple Slack bot that uses the OpenAI Agents SDK to interact with Model Context Protocol (MCP) servers. It is aimed at developers who want to bring AI-powered agent interactions into Slack channels.

How to use agentic-slackbot?

Install dependencies with uv sync, set required environment variables (OpenAI API key, Slack tokens, model name), then run the bot with uv run bot. A Docker image can be built and run using the provided Dockerfile and environment variables.

Key features of agentic-slackbot

- Integrates with Model Context Protocol (MCP) servers
- Uses OpenAI Agents SDK for AI interactions
- Supports custom OpenAI models and Azure OpenAI
- Configurable via environment variables
- Supports Langfuse observability
- Docker deployment ready

Use cases of agentic-slackbot

- Provide a Slack bot that leverages OpenAI agents and MCP server tools to automate conversations or tasks.

FAQ from agentic-slackbot

Details

Author
john-lin
GitHub stars
5
Category
agent-framework
Repository
john-lin/agentic-slackbot

agentic-slackbot

A simple Slack bot that uses the OpenAI Agents SDK to interact with the Model Context Protocol (MCP) server.

Install Dependencies

uv sync

Environment Variables

Create a .envrc file in the root directory of the project and add the following environment variables:

export OPENAI_API_KEY=""
export SLACK_BOT_TOKEN=""
export SLACK_APP_TOKEN=""
export OPENAI_MODEL="gpt-4o"
export HTTP_PROXY=""

If you are using Azure OpenAI, you can set the following environment variables instead:

AZURE_OPENAI_API_KEY=""
AZURE_OPENAI_ENDPOINT="https://<myopenai>.azure.com/"
OPENAI_MODEL="gpt-4o"
OPENAI_API_VERSION="2025-03-01-preview"

If you are using Langfuse

export LANGFUSE_PUBLIC_KEY="xxx"
export LANGFUSE_SECRET_KEY="xxx"
export LANGFUSE_HOST="xxx"

Running the Bot

uv run bot

Running the bot in docker

bash

Build the Docker image


docker build . -t agentic-slackbot

Run the Docker container

docker run -e SLACK_BOT_TOKEN="" \ -e SLACK_APP_TOKEN="" \ -e HTTP_PROXY="" \ -e OPENAI_PROXY_BASE_URL="" \ -e OPENAI_PROXY_API_KEY="" \ -e OPENAI_MODEL=gpt-4o \ -e FIRECRAWL_API_URL="" slackbot ```

Credit

This project is based on the sooperset/mcp-client-slackbot example.