mcpbeat

Kanban AI MCP Server

io.github.orholam/kanban-ai
not responding

Kanban AI is listed as active in the registry but did not answer our last check. Last commit 29 Jul 2026.

Remote MCP for Kanban AI boards—manage projects, tasks, and comments from AI tools.

Uptime history 42 hours of history · worst hour 0%
42 hours agonow
0.0%
Uptime 24h
0 of 91 checks
—
Tools
hidden behind auth
83 ms
Response time
average over 24h
1
Stars
last commit 29 Jul 2026

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 12 min ago.

run in your terminal
claude mcp add kanban-ai --transport http https://kanbanai.dev/api/mcp
~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "kanban-ai": {
      "url": "https://kanbanai.dev/api/mcp"
    }
  }
}
~/.codex/config.toml
[mcp_servers.kanban-ai]
url = "https://kanbanai.dev/api/mcp"
.cursor/mcp.json
{
  "mcpServers": {
    "kanban-ai": {
      "url": "https://kanbanai.dev/api/mcp"
    }
  }
}
.vscode/mcp.json
{
  "mcpServers": {
    "kanban-ai": {
      "url": "https://kanbanai.dev/api/mcp"
    }
  }
}

Endpoints

URLTransportStateLatencyChecked
https://kanbanai.dev/api/mcp streamable-http answering 83 ms 12 min ago

Kanban AI — questions

Answers built from our own checks of this server.

Is Kanban AI working right now?
We send a real MCP handshake every 15 minutes. Over the last 24 hours 0 of 91 checks got a reply (0.0%), average response time 83 ms. The bar chart above shows every period we have measured.
The registry lists Kanban AI as active — why does it not respond?
The official MCP registry stores what the author submitted; it does not verify that the server still runs. We check the endpoint ourselves, and this one does not answer. Catalogues that copy the registry without checking will show it as working.
How do I connect Kanban AI?
Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.
Does Kanban AI need an API key?
No. Kanban AI completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. This is what we observed, not what the docs claim.
Is Kanban AI open source?
Yes — written in TypeScript and 1 stars on GitHub. The source link is on this page, so you can read exactly what it does with your data before you connect it.