
Features
AI Chat Connectors are in Beta at the moment. They are an early version and are subject to change. You can expect more functionality to be added over time.
Chat Connectors let you connect AI chat apps, like ChatGPT, Claude, Cursor, or Le Chat, to your Capacities space.
By using the Model Context Protocol (MCP) open standard, you can connect your Capacities space to allow access to your AI assistant of choice so that it may search, read objects, add content to your daily note and link objects in its responses. You can view all capabilities in detail in our developer docs.
In the setup process you'll give the tool of your choice access to a selected Capacities space. The AI can then interact with Capacities on your behalf.

Only the space that you select in this consent screen is the one that the tool will be able to access for that particular connection. If you would like to use multiple spaces from the same AI tool, you'll have to setup multiple MCP connections.
If you don't see a space in the consent screen, AI Assistant is not enabled for that space yet. Only spaces with AI Assistant enabled are shown and can be connected through MCP.
In the following are instructions for setting up the most popular AI tools.
We have applied to add our connector as a public option in OpenAI's app catalogue for easier setup. Until then, if you want to utilize ChatGPT you'll have to enable Developer Mode and add the MCP server URL directly. To do so:
Advanced Settings, and enable Developer mode. Note that this option is only available for ChatGPT's Pro, Plus, Business, Enterprise and Education accounts on the web. Read more here.Add App. Specify a name (ex. Capacities), and a description that will help the model contextualize the tools. For example:Capacities brings together connected note-taking and structured data so everything you care about becomes an object, whether it’s a person, a book you’re reading, a project you’re working on or an idea you want to explore. Objects have structure, properties and connections that grow into a living network of your thoughts.
https://api.capacities.io/mcp
We have applied to add our connector as a public option in Claude's connector catalogue for easier setup. Until then, if you want to utilize Claude you'll have to add the MCP server URL directly. To do so:
Customize → Connectors+, then Add custom connector. Give it a name (Ex: Capacities) and enter the URL:https://api.capacities.io/mcp
Connect and go through the authentication flow to connect to your space.claude mcp add --transport http capacities https://api.capacities.io/mcp
/mcp in Claude Code and following the authentication flow./mcp command to list and manage the MCP servers you have installed, and use the /context command to understand the context token usage of your current session, including the number of tokens used by each MCP server that’s enabled.Intelligence → Connectors+ Add Connector, then Custom MCP Connector.Capacities), and a description that will help the model contextualize the tools. For example:Capacities brings together connected note-taking and structured data so everything you care about becomes an object, whether it’s a person, a book you’re reading, a project you’re working on or an idea you want to explore. Objects have structure, properties and connections that grow into a living network of your thoughts.
https://api.capacities.io/mcp
Then click on Connect
Settings → MCP → Add new global MCP server{
"mcpServers": {
"capacities": {
"url": "https://api.capacities.io/mcp",
"auth": {
"CLIENT_ID": "cursor_mcp_capacities_public"
}
}
}
}
You can always configure the Capacities MCP server as a custom MCP client with any tool that supports the MCP protocol, please checkout our Model Context Protocol guide.
Missing any other apps we should have an official AI Chat Connector for? Please let us know via our feedback board.
After completing the authentication process for any AI tool, a new entry will appear in Settings > AI Assistant > AI Chat Connectors - Active Connections.
If you'd like to remove access for that tool, simply click on Disconnect on its entry. Note that this doesn't automatically remove it from the tool's connections. Likewise, removing the Connector from your AI tool won't automatically remove its access rights from Capacities.

Please check our AI Privacy page for details on our privacy with AI features.
You should expect more functionality to be delivered for Chat Connectors. You can read about our Roadmap on our MCP Server documentation.
If you’re implementing a custom MCP client (OAuth 2.1, PKCE, token refresh) to integrate Capacities into your own app/agent/bot, please refer to Model Context Protocol (MCP) instead.
Ask a question! - The Docs Assistant knows everything about the documentation, and the ideas and feature requests from other users.
Create a ticket on our feedback board. - Let us know if you have an idea for a feature, improvement or think there is something missing.
Request additions to the documentation. - If your questions are not getting answered, let us know and we will extend the documentation.