Connect Nuclino to AI Assistants with MCP

Who can use this feature?

🔐 All team members can configure this integration.

⭐️ Available on all plans.

Nuclino supports the Model Context Protocol (MCP), an open standard that lets AI assistants access your workspace content directly. This means you can ask your AI assistant to search your documentation, create new pages, or update existing content. All through natural conversation. For an overview, see Nuclino MCP.

What is MCP?

MCP is an open protocol that allows AI applications to securely connect to external data sources. When you connect Nuclino via MCP, your AI assistant can:

Search your workspaces for relevant information.
Read the full content of any page.
Create new items and collections.
Update existing pages.
Restore earlier versions of a page from its version history.
Organize content by moving items between collections and workspaces, or to the trash.
Comment on pages to leave feedback or ask questions.
Set up workspaces by creating new ones or changing their name and default view.
Attach files to pages, either from a public URL or from your computer.

All actions respect your existing permissions

The AI can only access what your account can access.

Connecting Nuclino to an MCP Client

MCP is supported by a growing number of AI applications, including Claude Desktop, Cursor, Windsurf, and others. The setup process varies by application, but generally involves adding the Nuclino server URL to your MCP configuration.

Server Details

Setting	Value
Server URL	`https://api.nuclino.com/mcp`
Authentication	OAuth 2.0 (handled automatically)

General Setup Steps

Open your AI application's MCP or integration settings.
Add a new MCP server with the URL https://api.nuclino.com/mcp.
Restart the application if required.
When you first interact with Nuclino through the AI, you'll be prompted to authorize access.
Sign in to your Nuclino account and approve the connection.

Example Configuration

Many MCP clients use a JSON configuration file. The Nuclino entry typically looks like this:

{
  "mcpServers": {
    "nuclino": {
      "url": "https://api.nuclino.com/mcp"
    }
  }
}

Refer to your AI application's documentation for the exact configuration format and file location.

Using an API Key (for clients without OAuth support)

If your MCP client doesn't support OAuth, you can authenticate using an API key instead. After creating an API key, you can configure your MCP client with the bearer token:

{
  "mcpServers": {
    "nuclino": {
      "url": "https://api.nuclino.com/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_API_KEY"
      }
    }
  }
}

Replace YOUR_API_KEY with the key you created.

Available Capabilities

Once connected, your AI assistant can use these tools to interact with Nuclino:

Tool	Description
`list_teams`	List all teams you have access to
`list_workspaces`	List workspaces, optionally filtered by team
`get_workspace`	Get details of a specific workspace
`create_workspace`	Create a new public or private workspace in a team
`update_workspace`	Rename a workspace or change its default view
`list_items`	List items in a workspace or team
`search_items`	Search for items by keyword in a workspace or team
`get_item`	Read the full content of an item
`create_item`	Create a new item or collection
`update_item`	Update an item's title, content, or field values
`edit_item_content`	Apply partial, line-based edits to an item's content
`list_item_versions`	List the saved versions of an item
`get_item_version`	Read the content of a saved version of an item
`restore_item_version`	Restore an item's content to a saved version
`move_item`	Move an item or collection into another collection, to a workspace root, or to another workspace of the same team
`delete_item`	Move an item to trash
`create_comment`	Start a comment thread on an item
`list_comments`	Read the comment threads of an item, including replies
`get_comment`	Read a single comment thread
`create_field`	Create a new field in a workspace
`update_field`	Update an existing field definition
`delete_field`	Delete a field from a workspace
`get_file`	Get metadata and download URL for attached files
`upload_file`	Upload a file from a public URL and attach it to an item
`create_file_upload`	Start uploading a local file to an item (step 1 of 2, returns the upload data for a direct upload to storage)
`complete_file_upload`	Complete a direct upload and attach the file to the item (step 2 of 2)

Example Use Cases

Once Nuclino is connected, you can ask your AI assistant things like:

"Search my Nuclino workspace for our API documentation"
"Create a new page in Nuclino titled 'Meeting Notes' with a summary of what we discussed"
"Find the onboarding checklist and add a new item for security training"
"What does our documentation say about deployment procedures?"
"Move the release checklist into the Engineering collection"
"Leave a comment on the onboarding guide asking who owns the security training section"
"Create a new workspace called 'Product Roadmap' that opens in the board view"
"Attach the PDF at this link to the release notes page and embed it below the summary"
"Show me what the deployment guide looked like last week and restore that version"

Managing Your Connection

You can view and manage your MCP connections from your Nuclino profile settings under API Keys. Each MCP connection creates an API key labeled with the application name (e.g., "MCP: claude.ai" or "MCP: cursor.com").

To disconnect an AI assistant from your Nuclino account, revoke the API key.

Security & Privacy

OAuth 2.0 with PKCE: Industry-standard secure authorization flow
Scoped Access: The AI can only access workspaces and teams your account has permission to view or edit
No Password Sharing: Your Nuclino password is never shared with third-party applications
Revocable: You can disconnect any application at any time from your account settings
Rate Limited: API access is rate-limited to prevent abuse

For Developers

If you're building an MCP client or integration:

Endpoint: https://api.nuclino.com/mcp
Protocol: MCP over HTTPS with JSON responses (stateless mode)
Authentication: OAuth 2.0 with PKCE
OAuth Metadata: https://api.nuclino.com/.well-known/oauth-authorization-server