Slack

Enables AI agents to post messages to Slack channels through the Model Context Protocol transport layer, which abstracts away HTTP/WebSocket complexity. The server implements MCP's standardized tool schema for message composition, handling authentication via Slack Bot tokens and translating tool invocations into Slack Web API calls. This allows Claude and other MCP clients to send formatted messages (text, blocks, attachments) without managing API credentials or rate limiting directly.

Provides AI agents with the ability to query available Slack channels, retrieve channel metadata (topic, description, member count, creation date), and list channel members through MCP tool invocations. The server caches channel lists to reduce API calls and implements filtering by channel name, type (public/private), or membership status. This enables agents to make context-aware decisions about which channels to post to or monitor.

Allows AI agents to fetch message history from Slack channels or direct messages, with configurable limits on message count and time range. The server implements context windowing to prevent token overflow in LLM prompts by truncating or summarizing older messages. It handles message formatting (converting Slack's rich text blocks into readable text), resolving user mentions and emoji, and optionally including thread replies. This enables agents to understand channel context before taking actions.

Enables agents to query Slack user information by user ID, email, or display name, retrieving profile data such as real name, title, department, timezone, and status. The server implements user caching to reduce API calls and supports bulk user lookups. This capability allows agents to personalize messages, route tasks to appropriate team members, or understand organizational structure.

Provides agents with the ability to add or remove emoji reactions to Slack messages, enabling non-verbal communication and message categorization. The server validates emoji names against Slack's supported emoji set and handles reaction conflicts (e.g., duplicate reactions). This allows agents to acknowledge messages, mark items as complete, or categorize discussions without posting text.

The Slack MCP server implements the Model Context Protocol's transport layer to handle authentication, request/response serialization, and error handling for all Slack API calls. Rather than exposing raw HTTP requests, the server uses MCP's tool schema system to define Slack capabilities as discoverable, typed tools that clients can invoke. Authentication is managed server-side using environment variables or configuration files, eliminating the need for clients to handle credentials. The server implements request queuing and rate limit handling to respect Slack's API quotas.