# AI Agents - Kanera > Connect Claude, ChatGPT, Codex, Copilot, or Cursor to real Kanera work through a native MCP server, a CLI, and a TypeScript SDK — with read-only credentials when you want them. Bring the AI you already use; Kanera ships no chatbot of its own. Canonical page: https://www.kanera.app/ai-agents Copy AI agent setup # AI agents welcome. They can do anything you can do. Ask Claude for your standup. Have Cursor file the bugs it found. Point ChatGPT at a board and get the status update you were going to chase six people for. MCP access for the agents you already use, scoped OAuth, and no bundled AI surcharge. [Start free](https://board.kanera.app/signup)[Connect an agent](https://www.kanera.app/docs/ai-mcp) Setup guides [Claude](https://www.kanera.app/docs/ai-mcp-claude)[ChatGPT](https://www.kanera.app/docs/ai-mcp-chatgpt)[Codex](https://www.kanera.app/docs/ai-mcp-codex)[GitHub Copilot](https://www.kanera.app/docs/ai-mcp-github-copilot)[Cursor](https://www.kanera.app/docs/ai-mcp-cursor)[OpenCode](https://www.kanera.app/docs/ai-mcp-opencode)[Gemini CLI](https://www.kanera.app/docs/ai-mcp-gemini-cli) What people ask it for ## The work you keep meaning to do and never quite get to. An agent connected to Kanera works from live boards across every workspace your identity can reach, not from a stale export or a summary someone pasted in. What changed on the Delivery boards this week? Weekly status without asking anyone The agent reads activity across every board you can see and writes the summary you would have chased six people for. What is overdue and who is blocked? Triage what slipped Cross-board queries over due dates, assignees, and completion, rather than opening each board and squinting at it. Prepare my standup from my Up next queue. Standup, prepared Your ranked queue and assigned work, read the same way the app reads it, turned into three sentences. Turn this thread into cards on the Support board. Capture without retyping The agent already has the conversation. It writes the cards, the checklists, and the labels in one pass. Which cards reference the auth migration? Find things you half-remember Search across cards, comments, notes, and attachments, then follow the links rather than reporting a list. Audit the release board before we cut 2.0. Check the work before it ships Unchecked checklist items, unassigned cards, stale columns. The pass nobody has time to do by hand. [More prompts and workflows](https://www.kanera.app/docs/ai-mcp-examples) Three ways in ## Whichever agent you have, there is a way in for it. All three reach the same work, and all three stay inside your permissions. Most people need only the middle one, and it takes about a minute. When your agent lives in a terminal ### The Kanera CLI Your coding agent is already in a terminal, working on the thing a card describes. One install later it can read that card, comment on it, and close it when the work lands — so the board keeps up with the branch without anyone stopping to update it. Useful for you too: see what is on your plate without leaving the editor. kanera setup claude also teaches your agent how to use Kanera properly. [CLI documentation](https://www.kanera.app/docs/cli) bash # install once npm install --global @kanera/cli kanera auth login   # then work kanera work kanera card done MKT-42 kanera comment MKT-42 "Shipped." Publishing to npm with the next release. The one most people want ### The MCP server Approve Kanera inside Claude, ChatGPT, Codex, Copilot, Cursor, OpenCode, or Gemini CLI once, in a browser — no key to create, nothing to paste — and from then on you just ask. It sees exactly what you see and nothing you cannot, and you can disconnect it from your profile at any point. Headless client with no browser? Device authorization is supported too. [Connect an agent](https://www.kanera.app/docs/ai-mcp) text # the hosted endpoint https://mcp.kanera.app/mcp   # or your own deployment https://mcp.your-kanera.example/mcp When you want to build it yourself ### The TypeScript SDK For the agent that runs every Monday morning, the bot inside your own product, or the script that does the reporting nobody wants to do. Typed, dependency-free, and MIT licensed, so it runs anywhere you deploy and raises no questions from a legal review. Signature checks, retries, and paging through long lists are already handled. [SDK documentation](https://www.kanera.app/docs/sdk) ts const kanera = new Kanera({ apiKey });   // every list endpoint iterates for await (const card of kanera.work.iterateCards()) { console.log(card.key, card.title); } Publishing to npm with the next release. Built for a moving target ## The best AI keeps changing. Yours should be free to. Almost every project tool bolted a chatbot into the corner, picked one model, and asked you to live with it. Twelve months later that choice looks dated and you are stuck with it. Kanera built the doors instead, so the AI on the other side is always the one you rate today — not the one we happened to sign with. Use the one you already know You have a favourite. Your designer has a different one, and your engineers have opinions about both. Nobody has to learn a second-rate assistant bolted into a project tool just to get their work updated — everyone brings what they are already fluent in. Swap it whenever something better lands Kanera speaks MCP, REST, and a plain command line — the standards agents already use. When the thing everyone is talking about next quarter arrives, you point it at the same address and carry on. No migration, and no waiting for us to add an integration. It gets better without us shipping a thing Every time your agent gets smarter, faster, or picks up a new skill, your Kanera workflow gets it too — the same afternoon, at no cost to you. A bundled chatbot only improves when the company that bundled it decides to improve it. What it costs ## All of this is just part of Kanera Pro. $5 per user per month, and everything on this page comes with it. No AI add-on, no per-agent fee, no usage meter running in the background while your assistant reads a board. Start the 30-day trial from your settings page and you can have an agent connected before lunch. Host Kanera yourself and it is simply switched on, with no plan checks anywhere in it. [See pricing](https://www.kanera.app/pricing)[Run it yourself](https://www.kanera.app/self-hosted-trello-alternative) Hosted Connect an agent in a browser and you are done. We run the address it talks to, keep it up, and keep it current. Included in Pro and the trial. Self-hosted Run Kanera on your own hardware and everything here comes with it — your own agent address, the same tools, no plan checks, and nothing leaving your network that you did not send. Common questions ## Questions about Kanera and AI Which AI agents work with Kanera? Any MCP-compatible client. Kanera publishes setup guides for Claude, ChatGPT, Codex, GitHub Copilot, Cursor, OpenCode, and Gemini CLI, and the hosted MCP endpoint works with anything else that speaks the protocol. Agents that can only run shell commands do not need MCP at all. They can use the Kanera CLI, which exposes every MCP tool as a command. Do I need to be a developer? Not for MCP. Connecting Claude, ChatGPT, or Copilot is a browser consent screen and takes about a minute. The CLI and SDK are there for the cases where you do want to build something, and the API reference documents every endpoint if you would rather work directly against HTTP. Does Kanera have its own chatbot? No, and that is the point. The best AI changes every few months, and a chatbot bolted into a project tool is frozen at whatever its vendor picked. Kanera is built to be reachable instead: a native MCP server, a CLI, a TypeScript SDK, a complete REST API, and a published Agent Skill. So you use the assistant you are already fluent in, your colleague uses theirs, and when something better lands next quarter you point it at the same address and carry on. How does an agent connect? Use browser-based OAuth for a personal assistant when the client supports it. Use device authorization for a CLI or SSH session that cannot open a browser redirect. Use an unattended service connection for CI, cron, or server-side automation, and an API key for local clients or those that only accept a static credential. What can an agent see? Exactly what the credential can see, and nothing more. A personal connection follows your current board access across workspaces, standalone boards, and guest boards, including your private personal notes. An unattended service connection stays scoped to the single workspace or standalone board where it was created. Can I stop an agent from changing my work? Yes. Create the personal API key as Read-only. That credential can list, read, search, and report, and Kanera refuses every write with a 403 at the API. This matters because the refusal does not depend on the AI client honouring its own tool permissions. A confused or prompt-injected agent still cannot change a card, because the server will not let it. Will an agent make a mess of my boards? Changes made through the API, MCP, or the CLI are recorded in card history like any other change, so you can see what happened and when. For anything broad or sensitive, ask the agent to show a plan first, and give it a read-only credential until you trust it. Is agent access included in my plan? Agent access is part of Pro, the 30-day Pro trial, and self-hosted Kanera, which has no plan checks at all. A hosted Free organisation can start the trial from its settings page and connect an agent the same day. If a hosted organisation later moves to Free, Kanera revokes its API keys and pauses its connections rather than deleting them. Upgrading again restores what was switched off. Is my data used to train a model? Not by Kanera. Kanera never sends your work to a model provider, because Kanera does not call one. When you connect an agent, your data goes wherever that agent sends it, under that vendor's terms. That is your choice to make and your relationship to manage, which is the point of keeping AI out of the product. Can I run all of this on my own hardware? Yes. Self-hosted Kanera exposes its own MCP address, its own API, and works with the same CLI and SDK. Point them at your deployment and no request leaves your network except the ones your agent makes to its own model provider. Get started ## Bring the agent. We built the door. Connect in a browser with OAuth, or hand a read-only key to something that runs unattended. Either way, your work stays in Kanera and your choice of model stays yours. [Start free](https://board.kanera.app/signup)[Connect an agent](https://www.kanera.app/docs/ai-mcp) ## Machine-readable resources - [Kanera AI index](https://www.kanera.app/llms.txt) - [Kanera documentation index](https://www.kanera.app/docs/llms.txt) - [Agent discovery guidance](https://www.kanera.app/agents.md)