Kagan runs on your own machine — the client starts it, so there is no endpoint to ping. 243 installs a week from pypi.
AI-powered Kanban TUI for autonomous development workflows with agent orchestration
The linked repository no longer exists on GitHub — it was deleted or made private.
We have not read this server's code yet, 16 d ago · rules ccca72095570
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
export function spawn(options: Spawn): Promise<Thread>;
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add kagan -- uvx kagan
{
"mcpServers": {
"kagan": {
"command": "uvx",
"args": [
"kagan"
]
}
}
}
[mcp_servers.kagan]
command = "uvx"
args = ["kagan"]
{
"mcpServers": {
"kagan": {
"command": "uvx",
"args": [
"kagan"
]
}
}
}
{
"servers": {
"kagan": {
"type": "stdio",
"command": "uvx",
"args": [
"kagan"
]
}
}
}
Optional settings from the registry entry, left out of the block above:
KAGAN_OPENAI_API_KEY (OpenAI API key for agent execution (if using OpenAI backend)), KAGAN_ANTHROPIC_API_KEY (Anthropic API key for agent execution (if using Claude backend)), KAGAN_DB_PATH (Custom path for Kagan database file).
Kanban for agentic development over MCP — annotate any UI element into a ticket with file and line.
Integrates agents with Linear software development workflows.
A Jira-lite MCP server that guides planning-first workflows for AI-assisted development.
Work management with Spec-Driven Development: tasks, sprints and SDD approvals for coding agents.
Shared memory + orchestration for your coding agents. Local-first MCP, vector RAG.
Task management for AI agents with hierarchical tasks, dependencies, sprints, and coordination.
Task and sprint coordination for humans and AI agents, with scoped API keys and full audit trail.
Per-env roadmap board for WithVibe — an MCP server the orchestrator drives to plan and track work.
Answers built from our own checks of this server.