Learn how to connect AI assistants like ChatGPT or Claude to your Slite workspace using the Model Context Protocol , an open standard that lets AI tools interact with your knowledge base. The Slite MCP lets AI assistants search, retrieve, and create docs in your workspace.
Think of it as giving your AI assistant permission to access to your team's knowledge base, so it can answer questions using your docs and help you create new ones.
It works with any MCP-compatible AI tool like Claude, ChatGPT, Cursor and more.
Instead of searching through multiple docs yourself, ask your AI assistant and it'll find the answers for you.
Your team spends less time hunting for information and more time using it.
Pull information from across your workspace to create new onboarding guides, customer announcements, or internal reports.
What used to take hours of research and writing now takes minutes.
Interact with your Slite workspace directly from your favorite AI assistant to avoid context switching.
These are example prompts you could send to your AI assistant once the Slite MCP is connected:
- "Summarize our Q1 product updates and draft a customer announcement."
- "What's our policy on remote work?"
- "Draft an onboarding guide using our HR docs."
The Slite MCP supports OAuth authentication so getting started is easy. You'll just need to add the following URL as a custom MCP connector in your AI assistant’s settings:
Go to , then enter the Slite MCP URL above as well as a name. The advanced settings can stay blank.
Sign in to your Slite account and authorize Claude.
In the web app, go to , and enable .
Create a new app with the Slite MCP URL.
Select the OAuth authentication option
Sign in to your Slite account and authorize ChatGPT.
Add https://api.slite.com/mcp as a remote MCP server URL and complete the OAuth authentication when prompted.
Here are the tools you can currently use with the Slite MCP.
Add content blocks to existing docs
Get answers from your docs
Create a new channel (top-level container for docs)
Create a collection database with columns
Start a new comment thread on a doc, optionally anchored inline to a specific text span
Create new docs (with optional parent/channel)
get-comment-thread-on-note
Retrieve a specific comment thread on a doc, including all replies
Retrieve full content of a specific doc
List all sub-docs under a parent
Get user group details by ID
List all accessible channels in workspace
List comment threads on a doc, with filtering by resolved/unresolved state
list-empty-notes-for-knowledge-management
List empty docs for knowledge management cleanup
list-inactive-notes-for-knowledge-management
List inactive docs for knowledge management cleanup
list-notes-for-knowledge-management
List docs with knowledge management filters
list-public-notes-for-knowledge-management
List public docs for knowledge management
list-recently-edited-notes
Show docs you recently edited
list-recently-visited-notes
Show docs you recently viewed
Edit a specific block within a doc, in place
Replace a range of consecutive sibling blocks within a doc
Move a doc to a different channel or parent
Delete specific blocks from a doc
Post a reply to an existing comment thread
Mark a comment thread as resolved
Find docs by keyword across your workspace
Find users by name or email
Set the review state and/or review owner of a doc
Reopen a previously resolved comment thread
Update a channel's name, icon, or visibility
Add or remove columns in a collection database
Update title or content of existing docs
You may be able to control which tools your AI assistant can access, depending on your client.
Go to , then review when Claude is allowed to use the tools.
- Always allow — Claude can use this tool without prompting you
- Needs approval — Claude will ask before using this tool
- Blocked — Claude cannot use this tool
Tool management varies by client. Check your AI assistant's documentation to see if and how you can enable or disable individual tools for a connected MCP server.