01 Find
Bring the right work into context
Let an agent list and search actions, inspect status and due dates, and follow the structure around the work.
Model Context Protocol
Give AI the context behind the work.
Connect compatible AI agents to your actions, notes, and long-term knowledge—without copying context between tools.
Start for free Secure connection
Your AI agent
“What should I move forward today?”
The agent asks with the goal in view.
MCP
Permissioned context, on demand
OAuth · Read / write scopes
Your workspace
Launch research
In progress · Today
Interview notes
Tagged · Research
Decision context
Long-term note
What agents can do
From finding context to moving the work.
MCP turns ActionDrivenNote into a working memory an agent can use, while authorization keeps access explicit.
02 Read
Read the thinking behind an action
Open an action document as Markdown, including the notes and useful context collected while the work was moving.
03 Act
Move work forward with permission
Create and update actions, edit documents, manage tags, and attach files when write access has been approved.
Connect
One URL. Your account. Your permission.
Add the remote server to a compatible MCP client. Authentication happens through ActionDrivenNote in your browser.
Server URL
https://app.actiondrivennote.com/api/mcp- 01
Add the server
Paste the URL into the remote MCP server settings in your AI client.
- 02
Sign in
Use your ActionDrivenNote account when the authorization page opens.
- 03
Review access
Approve the requested read or write permission, then return to the client.
Questions
Before you connect.
What is MCP?
Model Context Protocol is an open way for AI applications to connect to external tools and data. ActionDrivenNote uses it to make your work context available to compatible AI clients.
Do I need MCP to use ActionDrivenNote?
No. ActionDrivenNote works as a planning and note-taking app on its own. MCP is optional and is only needed when you want an AI client to work with that context.
Can an AI agent change my data?
Only when write access is granted. MCP clients can request read access or read-and-write access, and ActionDrivenNote shows an authorization step before connecting.
Which MCP clients can connect?
Use a remote MCP client that supports HTTP transport and OAuth authorization. Add the ActionDrivenNote server URL in the client, then follow its sign-in flow.
Shared working memory
Give the agent context that survives the chat.
Start with your own actions and notes. Connect an agent when you are ready.