Connect Kanera to your AI agent
Kanera's MCP server lets the AI tools you already use search, plan, summarize, and update real Kanera work across every board you can access. Ask in plain language; the agent reads live cards, assignments, notes, and activity instead of guessing from pasted text.
AI agent connections work on every hosted plan, including Free, at up to 5 requests per second and 60 per minute per person on Free boards. Pro raises that to 20 and 400 and adds unattended service agents. See Rate limits.
Connect in under a minute
For ChatGPT and supported Codex surfaces, install Kanera by Happen Software Limited from the Plugins directory. The plugin includes the MCP connection and Kanera skill. Follow Set up ChatGPT or Set up Codex.
For other clients or a manual setup, pick the path below. Both use OAuth, so you sign in to Kanera and approve access in your browser; there is no API key to create or store.
Coding agents
For manual setup, paste one instruction into Codex, Claude Code, Cursor, Copilot, Gemini CLI, or OpenCode.
Fetch https://www.kanera.app/agent-setup/prompt.md and follow it.Other MCP clients
Add the hosted server address. A compatible client opens Kanera sign-in and consent.
https://mcp.kanera.app/mcpThe setup prompt installs Kanera's official Agent Skill, registers the hosted MCP server, and starts OAuth where the coding agent supports it. If an agent has shell access but no MCP client, the same prompt gives it the @kanera/cli fallback instead. Always review the Kanera consent screen before allowing access.
Running Kanera at your own address? Use the MCP address and setup prompt shown in Profile settings -> API keys in your Kanera, rather than the hosted defaults above.
Choose your AI client
Each guide gives the exact menu names, commands, configuration locations, and troubleshooting for one client.
Chat assistants
Coding agents and editors
Claude CodeAdd the hosted server with one command, then sign in from /mcp.CodexInstall the plugin in the desktop app or CLI; use MCP in the IDE.
GitHub CopilotAdd Kanera to Copilot agent mode in Visual Studio Code.
CursorAdd the hosted address to mcp.json and approve the browser sign-in.
Gemini CLIAdd the server with one command, then run /mcp auth kanera.
OpenCodeAdd a remote server entry; OpenCode starts OAuth on first use.Anything else
Try these first
Once connected, start with a question you would otherwise answer by opening several boards:
- "What is assigned to me across all my boards, and what is overdue?"
- "Summarize what changed on the Launch board this week."
- "Find every card that mentions the SSO migration and tell me who owns each one."
- "Show my Up next queue and suggest what to pick up first."
These only read Kanera. When you ask for a change, your AI client decides whether to confirm the write with you first, and Kanera checks that you are an Editor on the target board.
What you can do
Kanera MCP works across boards, assignments, ranked Up next queues, notes, comments, labels, custom fields, checklists, and activity. These workflows show where the connection is most useful.
Plan work, then track it as code lands
Read this repository and the "Upgrade dependencies" card. Write the implementation plan into the card, add one checklist item per project, and update each item after its build passes.
A coding agent can keep the shared card current while it works in the repository. Changes require Write access.
Prepare a standup from real progress
Prepare my standup across the boards I can access. Separate work completed yesterday, work in progress today, and blockers.
Combine personal work history with current cross-board assignments instead of inferring progress from card creation dates.
Review workload across boards
Show open work per person across this workspace. Flag overdue, unassigned, and stale cards, then suggest where work could move.
A bounded team-work query exposes assignment, overdue, unassigned, inactivity, and last-moved evidence without opening each board separately.
Show the board what the agent is doing
Open an agent run on PLAT-42 before you start, keep it updated as you go, and mark it blocked if you need a decision from me.
A run puts a live chip on the card naming the agent and the job, so a long task is visible while it happens rather than only once it lands. Requires Write access.
React when a card changes
Watch the Launch board. When a new comment asks a question, read the card and reply if the answer is in it; otherwise tell me.
A client that supports MCP event subscriptions, such as ChatGPT, is told about new cards, changes, moves, and comments and runs the task you described. Replying requires Write access.
Turn notes into structured work
Read my onboarding note and draft cards for each action item. Show the proposed fields before creating anything.
Use a draft, review, apply pattern. Reading and drafting are read-only; creating cards requires Write access.
See more practical prompts and workflows →
See what the agent did
Agent work is attributed to the agent
An AI agent connected through OAuth acts on your behalf, but Kanera does not record its work as yours. Comments, card changes, and activity rows it writes carry a via <agent> badge, you are notified about what it did, and Work Done keeps its output apart from your own. A personal API key used by your own script still acts as you, with no agent label.
Runs make in-flight work visible
Before multi-step work, an agent can open a run on the card with runs.start. The card tile then
shows a live agent chip, with the agent and the job in its tooltip, and the chip turns amber when the
agent is waiting on a person. A run that stops reporting is marked stalled after fifteen minutes, and
a finished run becomes a row in the card's activity.
See Agent runs and attribution for run states, card detail, notifications, and Work Done, and Work with coding agents from the terminal for the loop from a shell.
Why Kanera MCP
Kanera exposes more than single-board card operations:
- Work across your accessible boards. Personal OAuth connections and personal keys follow your current board permissions across workspaces, standalone boards, and guest boards.
- Use the right identity for the job. Connect as yourself with OAuth, create a scoped unattended agent for CI or cron, or use an API key for a local or custom deployment.
- Manage complete workflows. Work with cards, ranked Up next queues, checklists, comments, labels, custom field values, assignments, notes, attachments, activity, completed work, portfolio summaries, and bounded bulk card actions.
- Keep sensitive automation narrow. Personal OAuth connections are read/write-capable so they work consistently across MCP clients, while the client decides which tools the user can invoke and when to ask for approval. API keys and unattended agents can still be capped at Read. Workspace setup stays in the Kanera interface.
- React to changes, not just requests. A client that supports MCP event subscriptions, such as ChatGPT, can watch a board or card and act when a card is created, changed, moved, or commented on, or when your own Up next queue changes. See Subscribe to events.
- Give the agent product guidance. The official Agent Skill teaches safe discovery, stable ID resolution, idempotency, permission handling, and Kanera's workspace model.
Access at a glance
| Connection | Acts as | Best for |
|---|---|---|
| OAuth | You, within your current Kanera permissions | ChatGPT, Claude, Codex, Copilot, and other personal assistants that support remote MCP OAuth |
| OAuth device code | You, within your current Kanera permissions | A CLI, SSH session, or headless machine that cannot open a browser redirect |
| Unattended agent | A workspace service identity limited to the access level selected by an administrator | CI, cron, and server-side automations |
| Personal API key | You, across the boards you can access, capped by the key's Read or Write scope | Local MCP clients and custom personal integrations |
| Kanera CLI | The credential it holds | An agent that can run shell commands, or a local stdio MCP server via kanera mcp |
| Workspace or board API key | The workspace or standalone board where the key was created | Shared integrations that need a fixed destination and centrally managed scope |
Personal OAuth and device-code connections are read/write-capable. Your AI client controls which Kanera tools are available to you and when a write needs confirmation; Kanera then enforces your current role on the target board. For unattended automation or static credentials, use a Read-scoped service connection or API key when changes are not required. Configure workspaces, boards, lists, labels, fields, options, retention, and list ordering in the Kanera interface; agents can manage board-specific separators and their card-relative positions. Use a separate API key with the public REST API when a deliberately built integration genuinely needs another supported administration operation.
Go deeper
Set up and secure
- Connect an AI agent with OAuth or an unattended service connection
- Agent permissions and security
- Frequently asked questions: what an agent can see, change, and delete, and how to disconnect it
Use it well
- Browse practical prompts and workflows
- Agent runs and attribution
- Work with coding agents from the terminal
Reference