What is kanbantool-mcp CLAUDE.md?

A set of project instructions for a coding agent working on a Python server that connects to Kanban Tool, a task-board service. It explains the project setup, commands, available tools, and API details.

Use it when developing or maintaining this Kanban Tool connection, including running tests, checking code quality, and working with boards, tasks, comments, and subtasks.

It gives the agent the project-specific context needed to run, test, check, and safely modify the server without guessing how it works.

How VeryLongOrgNameSuchWow/kanbantool-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to VeryLongOrgNameSuchWow/kanbantool-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/VeryLongOrgNameSuchWow/kanbantool-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/VeryLongOrgNameSuchWow/kanbantool-mcp

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/verylongorgnamesuchwow/kanbantool-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/verylongorgnamesuchwow/kanbantool-mcp/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/verylongorgnamesuchwow/kanbantool-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/verylongorgnamesuchwow/kanbantool-mcp/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/verylongorgnamesuchwow/kanbantool-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/verylongorgnamesuchwow/kanbantool-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 2,118 This file is loaded in full into every session.

When invoked 2,118 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.02118	$0.02118
Opus 5	$0.01059	$0.01059
Sonnet 5	$0.00424	$0.00424
Haiku 4.5	$0.00212	$0.00212

Measured 11d ago against content hash 8f91a9234c92, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

kanbantool-mcp CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 98 lines

How it starts

The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Project

kanbantool-mcp is a FastMCP-based MCP server that bridges Claude Code with the Kanban Tool API v3 (https://kanbantool.com/developer/api-v3). Stack: Python 3.11+, FastMCP, httpx, pydantic. Distributed via uvx.

Runtime configuration comes from two env vars: KANBANTOOL_DOMAIN (account subdomain prefix) and KANBANTOOL_API_TOKEN (bearer token).

Commands

All run through uv:

Run server: uv run kanbantool-mcp
Tests: uv run pytest
Lint: uv run ruff check .
Format check: uv run ruff format --check .
Type check: uv run ty check

Tool surface

The server exposes a curated ~12 tools, not every Kanban Tool endpoint. Surface stays small on purpose — pick the highest-leverage workflows for an LLM agent.

Read tools (M1):

list_boards
get_board
search_tasks
get_task
recent_changes

Write tools (M2):

create_task
update_task
move_task
archive_task
add_comment
add_subtask
list_subtasks
update_subtask
delete_subtask
reorder_subtasks

User discovery tools (post-M3):

whoami — current user (resolves "me" / "myself")
get_user — fetch one user by id
list_board_collaborators — board's user roster (no bulk list-users endpoint exists)

M4 — Completeness:

list_custom_field_definitions — per-board metadata for the 15 custom_field_* slots (label, type, enabled state); pair with Task.custom_fields[custom_field_N] for values
start_timer — start a per-user time tracker on a task (POST /time_trackers.json with board_id+task_id)
stop_timer — stop a timer (PUT, ended_at defaults to "now")
delete_timer — hard-delete a timer
list_my_timers — current user's time trackers across all tasks

M5 — Custom-field writes & comment polish:

set_custom_field — set or clear one of the 15 custom_field_N slots on a task. value=None clears (sends literal null on the wire — does NOT route through _patch_task because that helper has None-skip "omit, don't clear" semantics).
delete_comment — soft-delete a comment on a task. Returns the deleted Comment with deleted_at populated; mirrors the delete_subtask shape. The Kanban Tool API has no edit endpoint for comments (verified via spike: PUT/PATCH/POST-with-_method overrides all 404), so "fixing" a comment means delete + re-post. While in here, also fixed a P0 wire-field bug in add_comment — the body field is content, not text (every pre-fix call 422'd Content can't be blank); the Comment model now declares content: str directly.

Read the full file on GitHub · 98 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

11d ago First seen · 98 lines · 2,118 tokens per session scan A 8f91a9234c92

Subscribe to this mod's changes

kanbantool-mcp CLAUDE.md is an instructions file published in the GitHub repository VeryLongOrgNameSuchWow/kanbantool-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 2,118 tokens to every session, about $0.0106 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

kanbantool-mcp: Instructions file for Claude Code