Slack

Provides Slack API access over an HTTP MCP endpoint to list channels, fetch history, post messages, and manage workspace data.
  • javascript

0

GitHub Stars

javascript

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.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

You have a Slack MCP Server that exposes Slack API interactions over an HTTP MCP endpoint. This server lets you list channels, fetch histories, post and edit messages, manage reactions, and query user details and other workspace data through a simple HTTP interface. It’s useful when you want to integrate Slack functionalities into an MCP client workflow without directly embedding Slack SDK calls in your application.

How to use

You interact with the Slack MCP Server through an MCP client by calling named tools exposed via HTTP endpoints. The server runs locally and exposes a health check, a tool discovery list, and a call endpoint to execute specific Slack-related actions. Start the server, obtain a Slack token, and then issue requests to trigger the desired tool with the required arguments.

How to install

Prerequisites: Node.js and npm installed on your machine. If you prefer a containerized setup, you can run the Docker commands provided.

  1. Ensure you have a Slack Bot Token (xoxb-... for bot tokens or xoxp-... for user tokens). You will pass this token to the server via an environment variable.
export SLACK_TOKEN=xoxb-your-token
  1. Install dependencies and start the HTTP MCP server locally.
npm install
npm run start:http
  1. (Alternative) Run the server using Docker.
docker build -t slack-mcp .
docker run -d -p 3929:3929 -e SLACK_TOKEN=xoxb-your-token slack-mcp

Additional sections

Endpoints you will use while integrating with the MCP client are as follows: health at GET /health, tools at GET /tools, and tool execution at POST /call. You will perform calls by posting JSON that specifies the tool name and its arguments.

Environment and permissions: you must provide a valid Slack token via the SLACK_TOKEN environment variable. The server requires this token to access Slack APIs.

Token scopes required vary by the token type. For Bot Tokens (xoxb-...), you typically need channels:read, channels:history, chat:write, users:read, reactions:write, and optionally search:read for query operations. For User Tokens (xoxp-...), the same scopes apply and may include additional scopes based on your use case.

Common usage patterns include listing channels, retrieving channel history, posting or editing messages, adding reactions, retrieving user information, listing workspace users, and searching messages. Each action corresponds to a tool exposed by the server.

Security and best practices

Keep your Slack token secure. Do not expose SLACK_TOKEN in client-side code or logs. Use server-side environment configuration and rotating tokens as needed.

Limit the token scopes to only what is necessary for your integration and periodically review permissions to reduce risk.

Troubleshooting

If you cannot reach the server, verify that it is running and listening on port 3929. Check your SLACK_TOKEN value and ensure it is correctly exported in the environment before starting the server.

If a tool call fails, confirm the tool name and required arguments you are sending match what is defined in the tool’s description and that the Slack token has the appropriate scopes.

Available tools

slack_list_channels

List channels in the Slack workspace.

slack_get_channel_history

Retrieve messages from a specific channel.

slack_post_message

Send a message to a channel.

slack_update_message

Edit an existing message.

slack_delete_message

Delete a message from a channel.

slack_add_reaction

Add an emoji reaction to a message.

slack_get_user_info

Get details about a user.

slack_list_users

List users in the workspace.

slack_search_messages

Search messages across channels.

Built by
VeilStrat
AI signals for GTM teams
© 2026 VeilStrat. All rights reserved.All systems operational