slack-mcp
Read-only MCP server for Slack with OAuth 2.1 authentication, enabling message retrieval, thread replies, search, user and channel listing.
README
Slack MCP Server
A read-only MCP (Model Context Protocol) server for Slack with OAuth 2.1 authentication.
Demo
https://github.com/user-attachments/assets/211bd428-209f-461a-b9a1-9cc85fd7c438
Available Tools
slack_get_channel_messages- Retrieve messages from channelsslack_get_thread_replies- Get conversation thread repliesslack_search_messages- Advanced message search with filtersslack_get_users- List workspace users or get specific profilesslack_get_channels- List channels or get detailed info
Quick Start
1. Create Slack App
- Visit Slack API Apps and create a new app
- Under App Credentials, copy your
Client IDandClient Secret - Navigate to OAuth & Permissions and add these User Token Scopes:
channels:historygroups:historyim:historympim:historychannels:readgroups:readim:readmpim:readusers:readusers:read.emailsearch:read - Add Redirect URL under OAuth & Permissions:
- For local testing: Use an HTTPS proxy like ngrok (E.g:
https://abc123.ngrok.io/oauth2callback). See local development setup below. - For production:
https://your-domain.com/oauth2callback
- For local testing: Use an HTTPS proxy like ngrok (E.g:
2. Installation
uv sync
3. Local Development Setup (HTTPS Proxy)
Slack requires HTTPS for OAuth callbacks. For local development, use ngrok or a similar HTTPS proxy:
# Visit https://ngrok.com/ to download ngrok and start the proxy
ngrok http 8001
Copy the HTTPS forwarding URL (e.g., https://abc123.ngrok.io/oauth2callback) and add it as a Redirect URL in your Slack app settings.
4. Configuration
Set required environment variables:
export SLACK_CLIENT_ID="your_client_id"
export SLACK_CLIENT_SECRET="your_client_secret"
# Use https://your-domain.com for production.
export SLACK_MCP_BASE_URI="http://localhost"
# Use https://your-domain.com for production.
export SLACK_EXTERNAL_URL="https://abc123.ngrok.io"
# Optional, if you want to run the MCP server on a different port.
export SLACK_MCP_PORT=8001
5. Run the Server
uv run python main.py
The server will start on http://localhost:8001 by default. Make sure your ngrok proxy is running alongside it for OAuth to work.
6. Configure Your MCP Client
Add to your MCP client configuration (e.g. ~/.cursor/mcp.json for Cursor):
{
"mcpServers": {
"slack": { "url": "http://localhost:8001/mcp", "transport": "http" }
}
}
7. Authenticate
Authentication happens automatically via OAuth 2.1 when your MCP client first connects. Your client will open a browser window for Slack authorization — approve access and you're ready to go.
Deployment
For production deployment, you can run it inside docker:
docker build -t slack-mcp .
docker run -p 8001:8001 \
-e SLACK_CLIENT_ID="your_client_id" \
-e SLACK_CLIENT_SECRET="your_client_secret" \
-e SLACK_MCP_BASE_URI="https://your-domain.com" \
-e SLACK_EXTERNAL_URL="https://your-domain.com" \
slack-mcp
Development
Run tests with uv run pytest.
License
This project is licensed under the Apache License 2.0 - see the LICENSE file for details.
Duolingo is hiring! Apply at https://www.duolingo.com/careers
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.