mcp-slack
Verified Safeby kazuph
Overview
A Model Context Protocol (MCP) server for integrating with Slack workspaces, enabling agents to interact with Slack data and actions.
Installation
npx -y @kazuph/mcp-slack@latest --transport stdioEnvironment Variables
- SLACK_MCP_XOXC_TOKEN
- SLACK_MCP_XOXD_TOKEN
- SLACK_MCP_XOXP_TOKEN
- SLACK_MCP_XOXB_TOKEN
- SLACK_MCP_PORT
- SLACK_MCP_HOST
- SLACK_MCP_SSE_API_KEY
- SLACK_MCP_PROXY
- SLACK_MCP_USER_AGENT
- SLACK_MCP_SERVER_CA
- SLACK_MCP_SERVER_CA_INSECURE
- SLACK_MCP_ADD_MESSAGE_TOOL
- SLACK_MCP_USERS_CACHE
- SLACK_MCP_CHANNELS_CACHE
Security Notes
The server handles sensitive Slack authentication tokens (xoxc/xoxd browser tokens or xoxp OAuth tokens) which are passed via environment variables. It implements an optional API key for SSE transport using `subtle.ConstantTimeCompare` to mitigate timing attacks. The 'conversations_add_message' tool is disabled by default and requires explicit environment variable configuration (`SLACK_MCP_ADD_MESSAGE_TOOL`) for safety, with options for whitelisting/blacklisting channels. It supports custom CA certificates and allows explicitly insecure TLS connections (with a strong warning). No obvious 'eval' or malicious obfuscation patterns were found. The use of browser session tokens ('stealth mode') inherently carries a risk as it relies on an active user session, but this is a documented feature and user's choice. Proper handling of `.env` files and secure storage of tokens is paramount.
Similar Servers
slack-mcp-server
Provides a Model Context Protocol (MCP) server for integrating Slack workspace data and communication capabilities with AI models and agents.
ms-365-mcp-server
Interacting with Microsoft 365 and Office services through the Graph API via a Model Context Protocol (MCP) server.
slack-mcp-client
This client bridges Slack with AI models and external tools via the Model Context Protocol (MCP), enabling AI to interact with real systems and data through Slack conversations.
tmcp
A server implementation for the Model Context Protocol (MCP) to enable LLMs to access external context and tools.