Skip to main content

MCP server bridging Claude Code with the Kanban Tool API v3.

Project description

kanbantool-mcp

An MCP server that connects Claude Code (and other MCP clients) to a Kanban Tool account.

CI PyPI Python License: MIT

Why this exists

Kanban Tool holds the authoritative state of your boards, tasks, and workflow — but an LLM can't see any of it without help. This MCP server gives Claude Code (and any other MCP client) read access to boards and tasks, search via Kanban Tool's query DSL, and write tools to create, update, move, archive, comment on, and break down tasks. The point: stop re-explaining your kanban state to the model on every interaction, and let it act on the board directly when you want it to.

Status

Alpha, approaching v1.0. The 25-tool surface is settled and exercised against a real Kanban Tool account via the Live Integration workflow. Pre-1.0 means the surface may still evolve based on real-world feedback — pin a specific version if you need stability across upgrades. See SEMVER.md for the v1.0 stability commitment (which surfaces are stable, which are not, deprecation policy).

Install

Configuration

Two environment variables, regardless of how you launch the server:

Variable What it is Where to get it
KANBANTOOL_DOMAIN Your account's subdomain prefix — acme for https://acme.kanbantool.com. The URL you log into.
KANBANTOOL_API_TOKEN Bearer token for the Kanban Tool API v3. Profile -> API tokens in your Kanban Tool account.

From git (current)

Add to your MCP client's mcp.json:

{
  "mcpServers": {
    "kanbantool": {
      "command": "uvx",
      "args": [
        "--from",
        "git+https://github.com/VeryLongOrgNameSuchWow/kanbantool-mcp",
        "kanbantool-mcp"
      ],
      "env": {
        "KANBANTOOL_DOMAIN": "your-account",
        "KANBANTOOL_API_TOKEN": "your-token"
      }
    }
  }
}

From PyPI

{
  "mcpServers": {
    "kanbantool": {
      "command": "uvx",
      "args": ["kanbantool-mcp"],
      "env": {
        "KANBANTOOL_DOMAIN": "your-account",
        "KANBANTOOL_API_TOKEN": "your-token"
      }
    }
  }
}

Tool reference

Tool Purpose Key params
list_boards List boards visible to the authenticated user.
get_board Fetch a board with its columns, swimlanes, and custom-field definitions. board_id
search_tasks Search tasks across boards using Kanban Tool's query DSL (e.g. @alice priority:high tags:bug). Forwarded to the API verbatim. query, board_id?, limit?, page?
get_task Fetch a task by id with headline metadata, subtask/comment counts, and tracked time. task_id
recent_changes Fetch the changelog feed for a board — the change-tracking primitive that stands in for webhooks (Kanban Tool ships none). Poll sparingly, always with since. board_id, since?
create_task Create a new task on a board. Optional kwargs are omitted when unset. name, board_id, description?, lane_id?, priority?, tags?, ...
update_task Partial update of an existing task; only kwargs the caller passes are sent. None means omit, not clear. task_id, name?, description?, priority?, ...
move_task Move a task between columns, swimlanes, or positions. At least one target must be set. task_id, column_id?, swimlane_id?, position?
archive_task Archive a task. Idempotent. task_id
add_comment Post a comment on a task. task_id, content
delete_comment Soft-delete a comment on a task. Returns the deleted comment with deleted_at populated. The API has no edit endpoint — delete and re-post if you need to change a comment. task_id, comment_id
list_subtasks List subtasks attached to a task. task_id
add_subtask Add a subtask to a task. task_id, name
update_subtask Partial update of an existing subtask — mark complete, rename, change assignee. None kwargs are omitted. subtask_id, name?, is_completed?, assigned_user_id?
delete_subtask Soft-delete a subtask. Returns the deleted subtask with deleted_at populated. subtask_id
reorder_subtasks Reorder all subtasks under a task. ids must include the full set in the desired order. task_id, ids: list[int]
whoami Fetch the authenticated user's profile — id, role flags, locale. Use to resolve "me" / "myself" in user requests.
get_user Fetch one user by id. user_id
list_board_collaborators List users with access to a board (the canonical user-discovery surface — the API has no bulk list-users endpoint). board_id
list_custom_field_definitions List the per-board metadata for the 15 custom_field_* slots (label, type, enabled state). Use to interpret the values surfaced on Task.custom_fields. board_id
set_custom_field Set or clear one of the 15 custom_field_N slots on a task. value=None clears (sends literal null). task_id, slot (1..15), value
start_timer Start a per-user time tracker on a task. task_id, board_id
stop_timer Stop a running time tracker. ended_at defaults to "now" if omitted. timer_id, ended_at?
delete_timer Delete a time tracker (hard-delete). Returns None. timer_id
list_my_timers List the authenticated user's time trackers across all tasks.

(ping exists as a transport smoke test; not listed above.)

Examples

These transcripts are illustrative — they show the shape of a session, not literal terminal output.

Read flow

User:      What's on my Engineering board right now?
Assistant: (calls list_boards)            -> finds "Engineering" with id 4217
           (calls get_board 4217)         -> reads columns: Backlog / Doing / Review / Done
           (calls search_tasks
              query="archived:false",
              board_id=4217)              -> 14 active tasks, grouped by column

           Engineering has 14 active cards. Doing (3): "Migrate auth to OIDC",
           "Flaky CI on macOS", "Add rate-limit headers". Review (2): ...

Write flow

User:      Create a high-priority task in Engineering called "Fix login bug",
           and leave a comment that I'm picking it up today.
Assistant: (calls list_boards)             -> resolves "Engineering" -> id 4217
           (calls create_task
              name="Fix login bug",
              board_id=4217,
              priority="high")             -> task id 88231 created
           (calls add_comment
              task_id=88231,
              content="Picking this up today.")

           Created "Fix login bug" (id 88231) in Engineering at high priority,
           and added your comment.

Development

git clone https://github.com/VeryLongOrgNameSuchWow/kanbantool-mcp.git
cd kanbantool-mcp
uv sync
uv run pytest
uv run ruff check .
uv run ty check

Tests are offline-only and mock HTTP via respx — no Kanban Tool account needed to contribute.

Documentation

File What it covers
CONTRIBUTING.md Local setup, conventional-commit rules, what a good PR looks like, how reviews work.
RELEASING.md Release flow end-to-end (conventional commits → release-please → PyPI), the GitHub App that auths release-please, and break-glass procedures for stuck release PRs.
SEMVER.md Compatibility commitment for v1.0+ — which surfaces are stable, which are unstable, deprecation policy.
SECURITY.md How to report security vulnerabilities (GitHub private security advisories).

License

MIT

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

kanbantool_mcp-0.7.0.tar.gz (156.7 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

kanbantool_mcp-0.7.0-py3-none-any.whl (28.3 kB view details)

Uploaded Python 3

File details

Details for the file kanbantool_mcp-0.7.0.tar.gz.

File metadata

  • Download URL: kanbantool_mcp-0.7.0.tar.gz
  • Upload date:
  • Size: 156.7 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.13

File hashes

Hashes for kanbantool_mcp-0.7.0.tar.gz
Algorithm Hash digest
SHA256 f1a1c8c857366bf52a7673c9dfce04b7277cdd48486b64da37b92b89959119c5
MD5 af233138bbb927adba4e392dda024783
BLAKE2b-256 a6a65a4646e083e769fe63381611a1a7d8f50568f8798b5c4e40ffaabf71a03a

See more details on using hashes here.

Provenance

The following attestation bundles were made for kanbantool_mcp-0.7.0.tar.gz:

Publisher: release.yml on VeryLongOrgNameSuchWow/kanbantool-mcp

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file kanbantool_mcp-0.7.0-py3-none-any.whl.

File metadata

  • Download URL: kanbantool_mcp-0.7.0-py3-none-any.whl
  • Upload date:
  • Size: 28.3 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.13

File hashes

Hashes for kanbantool_mcp-0.7.0-py3-none-any.whl
Algorithm Hash digest
SHA256 4211dc71fc4fe219449ca45e921159ce63f8259e26c31095d3f1b247a494091b
MD5 939199cdbc4db30f06d84ba4fc7c378d
BLAKE2b-256 d15c26fc5623ca0aeac726012f0ae6b1018673774593222fb9d0f45ff9bcb051

See more details on using hashes here.

Provenance

The following attestation bundles were made for kanbantool_mcp-0.7.0-py3-none-any.whl:

Publisher: release.yml on VeryLongOrgNameSuchWow/kanbantool-mcp

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page