Your agent and your computer on Context Board

An AI can work with your board in three ways. Your own AI app connects over MCP and works on the board from its own window. Claude in the board is a chat beside it. And the runner links your computer, so that chat, your briefs and your jobs run on the Claude Code or Codex you already pay for.

You can use any one of them, or all three.

Connect your AI app over MCP

The board is an MCP server. Its address is the same for every app.

https://board.contextbolt.com/mcp

Your app signs in with an Allow page, so there’s no key to copy. The page names the app, says whether it’s verified, and lists what it can do. It can read your boards, notes and tasks, add and change widgets and send them data, and post updates you’ll see on the board. Click Allow. You can disconnect it any time in Connect.

Open Connect, then Your AI, and pick your app. Its page has the steps with your board’s address filled in, and it turns green the first time the app reads the board.

Claude (web and desktop)

1. Copy your board’s address from the Claude page in Connect.
2. Open Claude’s connectors (Customize, then Connectors) and choose Add custom connector.
3. Name it Context Board, paste the address and finish adding it. Then choose Connect, and Allow on the board’s page.

On a Team or Enterprise plan, an owner adds it once in Organization settings, then each member connects with their own account.

ChatGPT

1. Copy your board’s address from the ChatGPT page in Connect.
2. In ChatGPT’s settings, open the connectors section, open Advanced settings and turn on Developer mode. The page in Connect has a button that opens ChatGPT’s settings.
3. Choose Create, name it Context Board, paste the address, keep OAuth and create it. Then Allow.

ChatGPT names these menus a little differently from plan to plan. If a label doesn’t match, the page in Connect has the current steps.

Claude Code

Run this once in your terminal.

claude mcp add --transport http --scope user context-board https://board.contextbolt.com/mcp

Then run this. Your browser opens the board. Click Allow.

claude mcp login context-board

Added it before? Run only the second command, or type /mcp in Claude Code and choose Authenticate. Start a new Claude Code session to use it.

Codex

Run this once in your terminal. Your browser opens the board. Click Allow.

codex mcp add context-board --url https://board.contextbolt.com/mcp

If the browser didn’t open, run codex mcp login context-board. Start a new Codex session to use it.

Cursor

1. On the Cursor page in Connect, choose Add to Cursor. Cursor opens and asks you to install it.
2. When Cursor shows Needs login beside it, click that and Allow.

Or add it to ~/.cursor/mcp.json yourself.

{ "mcpServers": { "context-board": { "url": "https://board.contextbolt.com/mcp" } } }

VS Code

1. On the VS Code page in Connect, choose Add to VS Code. VS Code opens and asks you to install it.
2. When VS Code asks to sign in, choose Allow. Then use it from Copilot Chat in agent mode.

Or add it to .vscode/mcp.json yourself.

{ "servers": { "context-board": { "type": "http", "url": "https://board.contextbolt.com/mcp" } } }

Windsurf and other MCP apps

Paste the address where your app adds a remote MCP server, and click Allow if the board’s sign-in page opens. In Windsurf, add it to mcp_config.json as "serverUrl": "https://board.contextbolt.com/mcp".

Apps that can’t sign in

Under Other ways on an app’s page, Make a link with a key gives you the board’s address with a key in it. It works without signing in, so treat it like a password. You can remove it any time in Connected.

Try it

Once it’s connected, ask it something.

“Read my Context Board and tell me what needs my attention today.”

What your agent can do on the board

Plain asks work. “Add this to my to-do list” finds your list. Every tool takes a widget’s title as well as its id, so the agent finds “the clock” or “my orders goal” the way you name it. When two things fit, it asks which.

• Read: the whole board, any widget, and the apps and services you connected, each through the tool that reads it.
• Build: add, change, arrange and remove widgets, and send them data. When no built-in widget fits, it writes a custom one.
• Connect: add free and public sources the board refreshes itself, and show data from the services you connected, live.
• Keep you posted: add and tick tasks, write notes, post an update on what it found, and say what it’s working on.
• Make it yours: set a theme or make a new one, and make or rename a board.

An agent can’t delete or share a board. It doesn’t need your keys, either. You connect a service once, in Connect, and the agent reads through that connection.

A few widgets are yours to add, because they read your own computer or a product you sign in to. AI usage, Needs you, Git activity, Agent job and Project file come from the gallery (press A), and the ContextBolt SEO and Bookmarks widgets come from Connect. The Agents template already has the first three.

Everything an agent does shows at once, with its name on it, and can be undone. Deleted widgets go to the trash for 30 days.

In Claude Code, the board’s make_widget and make_theme prompts work as slash commands.

Claude in the board

The chat opens beside the board. Open it with the Ask button at the top right, from the command bar, or with Ctrl J or ⌘ J. It builds widgets and themes from a description, using the same tools as an outside agent.

It runs one of two ways.

• On your own computer: with the runner linked, the chat runs on your Claude Code or Codex, on the plan you already pay for. No API key. See the next section.
• On your own API key: paste an Anthropic key to chat with Claude, or an OpenAI key to chat with Codex. The key stays in your browser and goes only to that provider. Your provider bills you for what the chat uses.

Every change it makes is in plain sight.

• Each tool call shows as a line in the chat that jumps to its widget.
• Undo this change (or Undo these changes) under a reply puts the widgets and boards back as they were before it. Data and sources the chat connected stay.
• Removing a widget, and anything that reaches a new address (an API, a feed, an embed, a picture), waits for you to say yes.
• A source that needs your key opens the board’s own form. Keys never pass through the chat.
• The conversation is kept in your browser, per workspace, and goes when you sign out.

Your computer (the runner)

The runner is a small program you set up once with one line. It keeps a connection to your board, starts with the computer, and lets the board’s chat, morning briefs and agent jobs run on your own Claude Code or Codex. It also feeds AI usage, Agent activity, Needs you and Git activity.

Link your computer

1. Open Connect, then Your AI, then Your computers.
2. Pick Windows, or Mac or Linux.
3. On the computer where you use Claude Code or Codex, open PowerShell or the Command Prompt on Windows, or Terminal on a Mac or Linux.
4. Copy the line from Connect, paste it there and press Enter.

It shows up in Connect as linked within a few seconds. The line brings Node.js itself if the computer has none, and the runner starts with the computer from then on. Its code works once, so each computer gets a line of its own.

If neither Claude Code nor Codex is signed in on that computer yet, Connect says so. Install one there and sign in, and it shows up within a minute.

Project folders

The chat, briefs and jobs can work in folders you choose, such as your notes or your code. Open Connect, Your AI, then Project folders. Each folder is chosen in your computer’s own folder picker.

• Read only: the agent reads its files and changes nothing.
• Read and write: the agent can change files as it works. Each file it changes or deletes is kept as it was, on your computer, for 30 days.

Take a folder back from the same list, and the agent can no longer use it.

More than one computer, or a server

Link each one with its own line from Your computers. Sessions, usage and git come from all of them. The main one runs your board’s chat, briefs and jobs, and its project folders. Choose Make it the main one to change it. While the main one is off, another that is on takes over.

What leaves your computer

From your sessions, only names, states and percentages. That means a session’s title and project, whether it’s working, done or waiting for you, and how much of each limit is left. Never what was said in a session.

Two widgets send a little more, and only if you add them. Git activity sends each repo’s name and branch, how many files have changes, and recent commits (their short hash, author and message), never your code. Project file sends the text of the one file you point it at, so it can show it.

A shared view of your board never shows your sessions, usage, jobs or brief settings.

To hide your sessions, turn off Show my Claude Code and Codex sessions in Settings, under Your computer.

Unlink a computer

In Connect, Your AI, Your computers, or in Settings, choose the unlink button beside the computer. Its sessions leave your board and the runner there stops.

Briefs and agent jobs

Both run on your linked computer, with your own Claude Code or Codex.

• Morning brief: turn on Write it every morning in the brief’s settings and pick a time. Your agent writes the one thing that matters today, what changed, what needs you and the three things to do first. Write it now runs it at once.
• Agent job: add an Agent job widget, or choose Give it a job in a Number, Chart, List or Table widget’s menu. Say what it does in your own words, and choose Every day, Every week or When I run it. Run now runs it at once, and the answer lands on the widget.

Only you give a widget its job or set a brief’s schedule. An agent can write a brief, never set one to run.

The AI usage widget

AI usage shows what’s left of each plan’s current five-hour window and its week, for Claude Code and Codex, as rings that empty as you use them. A ring is green at half or more, amber from a fifth, and red under that. Each says when it resets, like “resets in 1h 42m” or “resets Mon 9:00 AM”, and a model’s own weekly limit shows when your plan has one.

It reads what each app last heard from its own servers, so it fills after the app’s next use. Add it from the gallery, or start from the Agents template. More on the Claude Code usage and Codex usage pages.