Slite MCP
Connect your AI assistant to Slite using the Model Context Protocol (MCP) — an open standard that lets AI tools interact with external services. Slite offers two MCP integrations depending on what you want to do.
Not sure which one to use? Read the overview below — it'll take 30 seconds.
What is MCP?
MCP (Model Context Protocol) is an open standard that lets AI assistants like Claude, ChatGPT, Cursor, or Gemini connect to external tools and data sources. Instead of copy-pasting context into a chat window, your AI assistant can directly read from and write to connected services.
Slite has two separate MCP integrations, each serving a different purpose.
The two Slite MCPs
External Search MCP
Formerly "Super"
Lets AI assistants search across your connected sources from outside Slite — directly inside Claude, ChatGPT, Cursor, or any MCP-compatible tool.
Best for: Answering questions, retrieving docs, and pulling knowledge into your AI workflows without leaving your AI assistant.
Slite Docs MCP
Manage your knowledge base
Lets AI assistants create, edit, and organize docs directly inside your Slite workspace.
Best for: Drafting new docs, updating existing content, and managing your knowledge base through an AI assistant.
Which one should I use?
Ask your AI assistant questions answered by your Slite docs
External Search MCP
Pull knowledge from Slite into an AI workflow or prompt
External Search MCP
Create or update docs in Slite from your AI assistant
Slite Docs MCP
Organize or manage your knowledge base via AI
Slite Docs MCP
Do both — search and write docs from your AI assistant
Both MCPs (they work together)
Works with any MCP-compatible AI tool
Both integrations work with Claude, ChatGPT, Cursor, Gemini, Codex, and any other tool that supports the Model Context Protocol.
New to MCP? Think of it like giving your AI assistant a secure key to your Slite workspace. You stay in control — the AI can only do what you ask it to, and nothing is changed without your input.