slack
MCP server from bitovi/slack-mcp-server
claude mcp add --transport stdio bitovi-slack-mcp-server docker run -i --rm -e SLACK_BOT_TOKEN -e SLACK_USER_TOKEN bitovi/slack-mcp-server:latest \ --env SLACK_BOT_TOKEN="xoxb-your-bot-token-here" \ --env SLACK_USER_TOKEN="xoxp-your-user-token-here"
How to use
This Slack MCP server exposes a set of MCP tools that enable AI agents to read Slack content by providing Slack URLs and channel information. The server runs via Docker and communicates over the MCP protocol using Stdio transport, making it suitable for CLI-based agents and tools. Core capabilities include reading individual Slack messages (including their threads) by URL, listing recent channel messages with optional pagination, and performing workspace-wide searches when a user token is provided. The server automatically resolves user IDs to readable names and builds user mappings for mentions, improving the human-readability of results. To use, run the Docker image with the required Slack bot token (and optional user token for search), then issue MCP requests to the server via standard input/output as defined by the MCP protocol. Available tools include read_message, list_channel_messages, and search_messages (the latter requires the SLACK_USER_TOKEN).
How to install
Prerequisites:
- Docker installed and running
- Slack Bot Token (SLACK_BOT_TOKEN) with appropriate scopes
- Optional Slack User Token (SLACK_USER_TOKEN) for search capabilities
Install steps:
-
Pull the Docker image (recommended): docker pull bitovi/slack-mcp-server:latest
-
Run the container with tokens passed as environment variables: docker run -i --rm
-e SLACK_BOT_TOKEN=xoxb-your-bot-token-here
-e SLACK_USER_TOKEN=xoxp-your-user-token-here
slack-mcp-server:latest -
Verify the server is responsive (via MCP client) and use the available tools (read_message, list_channel_messages, search_messages).
If you prefer building from source or running locally without Docker, follow the repository's Go build instructions after cloning the repo:
- Ensure Go 1.21+ is installed
- Build the server binary (paths may vary): go build -o slack-mcp-server ./cmd/server
- Run the binary with appropriate environment variables, if supported by the build variant.
Additional notes
Tips and considerations:
- SLACK_BOT_TOKEN is required for all operations; without it, the server cannot authenticate with Slack.
- SLACK_USER_TOKEN is optional and only needed if you plan to use the search_messages tool. If omitted, search operations will fail with a helpful error.
- When using Docker, ensure the container has network access to Slack APIs and that the Bot/User tokens are kept secure and not exposed in logs.
- For private channels or DMs, make sure the Slack app (bot) is invited to relevant conversations to read messages.
- The server uses the standard MCP protocol; you can integrate it with Claude, other MCP-compatible agents, or any client that speaks MCP over Stdio.
- If you change tokens, restart the container to reinitialize authentication.
- Review Slack scopes required in configuration (channels.history, groups.history, im.history, mpim.history for reading; optional search:read for search).
Related MCP Servers
trpc-agent-go
trpc-agent-go is a powerful Go framework for building intelligent agent systems using large language models (LLMs) and tools.
station
Station is our open-source runtime that lets teams deploy agents on their own infrastructure with full control.
tiger-cli
Tiger CLI is the command-line interface for Tiger Cloud. It includes an MCP server for helping coding agents write production-level Postgres code.
gopls
MCP server for golang projects development: Expand AI Code Agent ability boundary to have a semantic understanding and determinisic information for golang projects.
kubernetes
A Model Context Protocol (MCP) server for the Kubernetes API.
gcp-cost
💰 An MCP server that enables AI assistants to estimate Google Cloud costs, powered by Cloud Billing Catalog API and built with Genkit for Go