What tokens are required to use slack-mcp-server?
You need a Slack Bot User OAuth Token (`SLACK_BOT_TOKEN`) and, optionally, a Slack User OAuth Token (`SLACK_USER_TOKEN`) for features like message search.
@MCP-Mirror
基本信息
Mirror of
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"ubie-oss_slack-mcp-server": {
"command": "npx",
"args": [
"@ubie-oss/slack-mcp-server"
]
}
}
}工具列表暂未提供
当前收录暂时没有可展示的工具列表,不代表服务没有工具。请查阅项目文档了解支持的能力。
点击上方按钮,在临时沙箱中运行此服务器并实时获取工具列表。
slack-mcp-server is a Model Context Protocol (MCP) server that enables AI assistants to interact with the Slack API through a standardized interface. It provides tools for reading and writing messages, managing reactions, and searching workspace content. It is intended for developers who want to integrate Slack capabilities into AI agents or assistants.
Install the package from GitHub Registry using npm install @ubie-oss/slack-mcp-server (requires a personal access token). Set the required environment variables SLACK_BOT_TOKEN (Slack Bot User OAuth Token) and optionally SLACK_USER_TOKEN (Slack User OAuth Token, needed for search). Run directly with npx @ubie-oss/slack-mcp-server or via node. Configure your MCP client by adding a JSON entry with the command, arguments, and environment variables.
You need a Slack Bot User OAuth Token (`SLACK_BOT_TOKEN`) and, optionally, a Slack User OAuth Token (`SLACK_USER_TOKEN`) for features like message search.
Install via `npm install @ubie-oss/slack-mcp-server`. The package is hosted on GitHub Registry, so you must configure a personal access token.
Add an entry to your client’s MCP configuration JSON with `"command": "npx"`, `"args": ["-y", "@ubie-oss/slack-mcp-server"]`, and an `"env"` object containing the required tokens.
Nine tools are provided: list channels, post message, reply to thread, add reaction, get channel history, get thread replies, get users, get user profile, and search messages.
Use `npm run dev` from the project directory to start the server with hot reloading. Run linting with `npm run lint` and fix issues with `npm run fix`.

MCP server and API for AI agents that work LinkedIn on accounts you own: search, connect, message and enrich, with limits enforced on our server.
SendRaven is email infrastructure for AI agents. Send, read replies as threads, run campaigns and automations, with limits on the API key.

Body language for AI agents, on your terms. A consented three-second phone gesture gives your agent an Aligned or Unaligned signal with confidence. You remain the authority.

Email inboxes for AI agents. Give an agent its own address in one call; it sends, receives and replies in threads, waits for a sign-up code and gets it back already extracted, and hands a conversation to a person when it

Postdom is an AI social media tool that turns your website into short videos, slideshows and posts, then publishes them.
评论