kumihimo
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@kumihimobraid the plan in myplan"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Kumihimo
組紐 — many threads in, one cord out.
Kumihimo is the Japanese craft of braiding many separate threads into a single cord. This tool works the same way: you lay out a plan as a graph of plain-text files, and Kumihimo braids that graph into a single, well-ordered prompt an LLM or coding agent can act on.
See it.
kumihimo editopens a live canvas — kind-colored nodes, dependency/membership/annotation edges drawn distinctly, drag to arrange, click to edit. The canvas follows the files: change a node in vim (or let Claude change it over MCP) and watch it move.Braid it.
kumihimo braidcompiles the graph into one deterministic prompt: topologically ordered, sectioned by milestone, every item stating its real prerequisites, the graph's own Mermaid diagram embedded.Let Claude drive it.
kumihimo mcpserves the plan over MCP — twelve tools to read, restructure, validate, braid, and list the crew — so an agent can maintain the plan it executes. This repo's own roadmap is a Kumihimo plan (plans/roadmap), its milestone prompts were braided, not hand-written, and the canvas below is that roadmap today — v0.1 and v0.2 built end to end, the crew (agents, skills, the training log) on the canvas, the release node still blocked on a human with a tag:
The files are the only source of truth — Markdown with YAML frontmatter, in
git, diffing cleanly. The editor, CLI, and MCP server are thin clients over
one operations layer; node positions live in a view.yaml sidecar so
arranging the graph never dirties a semantic diff.
Ten minutes
Kumihimo is not on a package index yet — install from source (Python 3.11+; Node 18+ only if you want the canvas):
git clone https://github.com/tzavislan/kumihimo
cd kumihimo
cd frontend && npm install && npm run build && cd ..
pip install .The npm line builds the live canvas and can be skipped — everything below
still works except kumihimo edit, which then serves the API with an honest
"frontend not built" page instead of the graph.
kumihimo new myplan
kumihimo edit myplan # live canvas at 127.0.0.1:8720
kumihimo add myplan build --kind task --title "Build the loader" --body "..."
kumihimo check myplan # cycles named with paths, dangling edges, field breaches
kumihimo braid myplan # one prompt on stdout — paste into your agentA node is a file:
---
kind: task
title: Rate-limit middleware
needs: [api-endpoints, pick-algorithm]
in: [ship-guarded-api]
effort: M
acceptance:
- 429 + Retry-After on breach
---
Middleware on every authenticated route. Fail *open* on Redis errors —
availability beats enforcement.…and the braid compiles the graph into one prompt — preamble, embedded Mermaid shape, settled decisions stated as constraints, every task with an honest After: line and Done when: checklist:
The core is domain-agnostic: it understands identity, prose, order (needs),
membership (in), and annotation (links) — everything else comes from
kinds you define in the manifest, fields and Jinja2 templates included.
An engineering pack (task, milestone, decision, risk, question) ships as the
default; examples/fieldnotes is a research plan whose
kinds live entirely in its own manifest.
Docs: https://tzavislan.github.io/kumihimo/ — tutorial, concepts, custom kinds, MCP setup, file formats.
Related MCP server: roadmap-skill
Development
uv sync
uv run pytest -q
uv run python tools/lint.py # the conventions linter CI runs
cd frontend && npm install && npm test && npm run build # only if you work on the canvasConventions (enforced in CI): CONVENTIONS.md. Contributions: CONTRIBUTING.md. Design record: PLAN.md. Releases: RELEASING.md.
License
This server cannot be deployed
Maintenance
Related MCP Connectors
Create, read and live-edit visual boards, Kanban plans, Gantt timelines and diagrams with AI agents.
Durable, user-controlled goals and governed plans for AI agents.
Create and improve live, shared interactive documents with your agent.
Shared control plane for AI coding agents — tasks, memory, decisions, file locks. 12 tools.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceProvides interactive visual plans for AI coding agents, allowing users to review, approve, and monitor execution in real-time.8 npm638MIT
- AlicenseBqualityFmaintenanceEnables AI agents and humans to collaboratively plan and manage tasks with a shared kanban and dependency graph, all stored locally.3141 npm79MIT
- -licenseNot gradedqualityNot gradedmaintenanceEnables local task planning and execution with DAG-based plans, multiple reasoning methods, and persistence for AI agents.-
- AlicenseAqualityAmaintenancePlan-bank MCP for AI agents and Notion. Agents read and write Markdown implementation plans with line + section addressing — no ad-hoc temp scripts.122 npmMIT