# Agent Kanban

> AI-native kanban board where agents pull tasks via MCP

- **Type:** MCP server
- **Install:** `agentstack add mcp-graywrk-agent-kanban`
- **Verified:** Pending review
- **Seller:** [graywrk](https://agentstack.voostack.com/s/graywrk)
- **Installs:** 0
- **Category:** [Integrations](https://agentstack.voostack.com/c/integrations)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [graywrk](https://github.com/graywrk)
- **Source:** https://github.com/graywrk/agent-kanban

## Install

```sh
agentstack add mcp-graywrk-agent-kanban
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Agent Kanban

[](README.md)
[](README.ru.md)

> **English** · [Русский](README.ru.md)

[](LICENSE)
[](https://www.python.org/)
[](https://modelcontextprotocol.io/)

An AI-native kanban board where agents (Codex, Hermes, etc.) pull tasks via
the Model Context Protocol. The board is passive — it never spawns or controls
agents. You point your agents at the board via MCP config, and they
self-serve tasks through `get_next_task` / `claim_task`.

## Why?

Most agent orchestrators **push** work: a dispatcher decides who does what and
sends it. Agent Kanban inverts this — the board is a passive **MCP server**.
Agents discover and claim work when they're ready, exactly like a developer
picks a ticket from a real kanban. This decouples "what needs doing" (the board)
from "who does it and when" (the agent), and works with any agent that speaks
MCP — no glue code per agent.

## Features

- **Pull-based MCP** — board exposes 11 tools (`get_next_task`, `claim_task`,
  `post_progress`, `request_review`, …) over the streamable-HTTP transport
- **Hard assignment** — reserve a task for a specific agent; others don't see it
- **Live progress feed** — agents stream diffs, text, artifacts, errors; you
  comment back and the agent reads your feedback on the next turn
- **Bilingual UI** — Russian / English, with a one-click language toggle
- **Review diffs** — the board collects `git diff base...branch` on
  `request_review` and renders it inline (Shiki syntax highlighting)
- **Design system** — dark-first, single-amber-accent UI built on tokens
- **Self-hosted** — FastAPI + PostgreSQL + React; ships as a Docker image

## Screenshots

  
    Board (dark)
    Card detail
  
  
    
    
  
  
    First-run setup
  
  
    
  

## Architecture

See `docs/superpowers/specs/2026-07-05-agent-kanban-design.md` for the full
design. Phase 1 MVP scope is documented in
`docs/superpowers/plans/2026-07-06-agent-kanban-phase1-mvp.md`.

## Quickstart (local dev)

### Prerequisites
- Python 3.11+
- `uv` (install: `curl -LsSf https://astral.sh/uv/install.sh | sh`)
- Node.js 20+ and `pnpm`
- PostgreSQL 16+ running locally

### 1. Database
```bash
createdb kanban  # or use docker: see docker-compose.yml
cp .env.example .env  # DATABASE_URL defaults to port 5436 (matches docker-compose ak-pg)
uv run kanban migrate
```

### 2. Backend
```bash
uv sync --extra dev
uv run kanban serve
```

### 3. Frontend (separate terminal)
```bash
cd web
pnpm install
pnpm dev   # http://localhost:5173, proxies to :7331
```

### 4. Point an agent at the board
Add to your agent's MCP config:

**Codex** (`~/.codex/config.toml`):
```toml
[mcp_servers.kanban]
url = "http://localhost:7331/mcp"
```

**Hermes** (`~/.hermes/config.yaml`):
```yaml
mcp_servers:
  kanban:
    url: http://localhost:7331/mcp
```

Then instruct your agent: "Check the kanban board for tasks via get_next_task."

## Agent workflow

1. Create a task in the UI. It starts in `todo`.
2. Drag it to the `READY` column. It's now available to agents via `get_next_task`.
3. Instruct your agent (e.g. Codex, Hermes) to check the board:
   - Call `get_next_task` to discover work.
   - Call `claim_task` to take it.
   - Call `post_progress` to report what it's doing.
   - Call `request_review` when ready for your review, or `complete_task` when done.
4. Watch progress events stream into the card detail view in real time.
5. Add comments to give the agent follow-up instructions; the agent reads them via `get_comments`.

Agents must pass their identifier as the `agent` argument to mutation tools
(`claim_task`, `post_progress`, `complete_task`, `request_review`, `post_comment`,
`post_artifact`, `set_task_branch`, `set_task_pr`). The board authorizes mutations
by checking `claimed_by == agent`.

## Coding tasks (git/PR)

For tasks that touch a git repo, set `repo_path` and `base_branch` when creating
the task. The board does NOT create branches or PRs — your agent does that with
its own git tools. The board records what the agent reports and renders a review
diff.

Agent workflow for a coding task:
1. `claim_task` — receives `repo_path` and (if set) `base_branch`.
2. Create a branch in `repo_path` with the agent's git tool.
3. `set_task_branch(task_id, agent, branch)` — record it so the UI shows it and
   the diff can be collected.
4. Commit work on that branch.
5. `request_review(task_id, agent, summary)` — the board runs
   `git -C  diff ...` once and stores the result as a
   diff event visible in the card's progress feed.
6. Open a PR with the agent's GitHub tool, then
   `set_task_pr(task_id, agent, pr_url, "open")`.
7. When merged, `set_task_pr(task_id, agent, pr_url, "merged")` then
   `complete_task`.

If `repo_path`, `base_branch` (or the project's `default_branch`), or `branch` is
missing, diff collection is skipped silently. If `git diff` fails, an error event
is recorded instead, but the review request itself still succeeds.

## Authentication

The board requires authentication. Two kinds of principals:

- **Users** (humans): log in with username + password via the web UI. Sessions are signed cookies.
- **Tokens** (agents): opaque bearer tokens, managed in the Admin panel. Each token is bound to an `agent_name`.

### First run

On first startup with an empty database, the UI shows a setup screen: choose an admin username + password (8+ chars) and submit. Alternatively, set `AGENT_KANBAN_BOOTSTRAP_ADMIN_PASSWORD` to create the admin headlessly (for automation). After setup, log in and go to Admin → Tokens to mint tokens for your agents.

### Pointing an agent at the board

Agents authenticate via a bearer token. In your agent's MCP config:

**Codex** (`~/.codex/config.toml`):
```toml
[mcp_servers.kanban]
url = "http://your-host:7331/mcp"
# Codex reads headers from config in newer versions; otherwise set the auth via env.
headers = { Authorization = "Bearer " }
```

**Hermes** (`~/.hermes/config.yaml`):
```yaml
mcp_servers:
  kanban:
    url: http://your-host:7331/mcp
    headers:
      Authorization: Bearer 
```

The token's `agent_name` MUST match the `agent` argument you pass to MCP tools. A token minted with `agent_name=codex` can call `claim_task(agent="codex")` but NOT `claim_task(agent="hermes")`.

### Production env vars

- `SESSION_SECRET` — signing key for session cookies. REQUIRED in production; set a long random string.
- `PUBLIC_URL` — the public base URL (e.g. `https://kanban.example.com`). Controls cookie `Secure` flag.
- `AGENT_KANBAN_BOOTSTRAP_ADMIN_PASSWORD` — first-run admin password (optional; if unset, the UI setup screen creates the first admin).

## Docker
```bash
docker compose up -d
```
Runs the app on :7331 with Postgres in an internal-only container (not exposed to
the host). The app connects to it over the compose network as `postgres:5432`.
For local dev against a host-visible Postgres, see the standalone container note
in "Database" above (port 5436).

## Contributing

Contributions are welcome. The design spec and phased implementation plans live
under `docs/superpowers/` — they're a good map of the architecture and intent.

```bash
# clone, then:
uv sync --extra dev          # backend deps + test tooling
cd web && pnpm install       # frontend deps
uv run pytest -q             # 112+ tests
cd web && pnpm build         # type-check + bundle
```

Please open an issue first for non-trivial changes, so we can align on scope.

## Credits

The UI is built on a design system inspired by
[Sergey Dmitriev's brand book](https://brandbook.graywrk.ru) — amber as the
single UI accent, dark-first, with semantic-only status colors.

## License

[MIT](LICENSE) © Sergey Dmitriev

## Source & license

This open-source MCP server is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [graywrk](https://github.com/graywrk)
- **Source:** [graywrk/agent-kanban](https://github.com/graywrk/agent-kanban)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** yes
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** yes
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: flagged — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/mcp-graywrk-agent-kanban
- Seller: https://agentstack.voostack.com/s/graywrk
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.