Announcing the Slack MCP server and Real-time Search API
We're excited to announce the release of not one, but two, major components designed to significantly enhance how Large Language Models (LLMs) and AI agents interact with your workspace data: the Slack Model Context Protocol (MCP) server and the Real-time Search (RTS) API!
Slack MCP Server
The MCP server enables AI agents to interact with Slack content through tools designed for LLM-driven discovery, configuration, and execution. Unlike APIs, the MCP server is built specifically for LLM consumption with robust descriptions and examples that return natural language responses. Refer to our documentation to learn more about the Slack MCP server.
Real-time Search API
The Data Access API has evolved into the Real-time Search API! This API allows users to access Slack data through a secure search interface, enabling third-party applications to retrieve relevant Slack data without storing customer information on external servers. Get started using the Real-time Search API with this guide or get straight to business with the method reference.
Scope updates to assistant.search.context
Along with these changes, the assistant.search.context API method has undergone a scope change. The assistant.search.context API method moved away from the single search:read scope to a set of granular search:read.* scopes:
search:read.public(required) - for public channel accesssearch:read.private- for private channels (with user consent)search:read.im- for direct messages (with user consent)search:read.mpim- for multi-party direct messages (with user consent)
This change allows for more granular control over what data AI-enabled apps can access.