Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
作者による説明(英語の原文)
Control Krita through a secure local MCP server and authenticated Windows bridge.
この3つを1つのスコアにまとめることはしません。意見、測定、人気はそれぞれ別のものだからです。
このサーバーのやさしい解説はまだ書いていません。以下はレジストリから読み取った事実です。
使っているAIアプリを選んで、設定をコピーしてください。
必要なもの
どのアプリを使っていますか?
上でアプリを選んでください。選んだアプリを覚えておくので、次からはボタンに「…にインストール」と表示されます。
Claude Desktop → Settings → Developer → Edit Config を開き、claude_desktop_config.json にこれを貼り付けます
{
"mcpServers": {
"krita-codex": {
"command": "uvx",
"args": [
"krita-codex-mcp"
]
}
}
}ターミナルでこれを実行します
claude mcp add krita-codex -- uvx krita-codex-mcpプロジェクトの .cursor/mcp.json、または ~/.cursor/mcp.json に貼り付けます
{
"mcpServers": {
"krita-codex": {
"command": "uvx",
"args": [
"krita-codex-mcp"
]
}
}
}ブラウザがアプリを開いてよいか確認し、そのあとアプリが設定を表示して確認を求めます。キーの値は空欄のままなので、自分で入力してください。
プロジェクトの .vscode/mcp.json に貼り付けます
{
"servers": {
"krita-codex": {
"type": "stdio",
"command": "uvx",
"args": [
"krita-codex-mcp"
]
}
}
}ブラウザがアプリを開いてよいか確認し、そのあとアプリが設定を表示して確認を求めます。キーの値は空欄のままなので、自分で入力してください。
これはパソコンで動くサーバーですが、ChatGPTがつなげるのはインターネット上のサーバーだけです。ほかのアプリを選んでください。
選んだアプリは、この端末のCookieに保存されます。アカウントは不要です。
この設定は、作者のレジストリ登録情報から作成しています。READMEと違う場合は、READMEに従ってください。
パソコンで動くサーバーです。インストールすると、ツール一覧がAIアプリに表示されます。
誰でも見られる情報をチェックしており、コードは読んでいません。当てはまらない項目は数に入れていません。 · 2026年11月7日にチェック
レジストリ名は、リポジトリを所有するGitHubアカウント cyyprezz で確認済みです
このリポジトリはまだGitHubから読み取っていません
このリポジトリはまだGitHubから読み取っていません
これはパソコンで動くため、インターネット上のエンドポイントはありません
パソコンで動き、代わりにローカルの設定を使います
パソコンで動くサーバーです。ツール一覧を読み取れるのは、インターネット上のエンドポイントがある場合だけです
レジストリでこのカテゴリにある有効なすべてのサーバーと比較しています。スターは、公開者がリポジトリの所有者である場合だけ数えます。
当てはまる基本チェック1項目のうち1項目に合格しました。コードは読んでいません。キーやトークンを追加する前に、サーバーがどんなアクセスを求めているかを確認し、必要な権限だけを持つキーを使ってください。
レジストリには必須のキーは載っていません。ただし、最初に使うときにサインインを求めるサーバーもあります。
あなたのパソコンで動きます。必要なときにAIアプリが起動し、データは作者のサーバーを通りません(サーバー自体がオンラインサービスを呼び出す場合を除きます)。
GitHubリポジトリの最終更新は–、最新バージョン(0.2.0)がレジストリに届いたのは4 か月前です。
Claude Desktop、Claude Code、Cursor、VS CodeなどのMCP対応アプリで使えます。パソコンにPython (uv)も必要です。
同じカテゴリには:Spec Driven Development, Remote Desktop Commander, Master CSS
同じカテゴリで、ほかの作者が作ったサーバー。スターの多い順。
カードの見方:★ GitHubスターi3つの柱:レビュー · チェック · 利用状況i更新=最新バージョンをレジストリに公開した日i
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Remote Desktop Commander: use files, terminal and processes on your own computers from any AI app.
Inspect Master CSS classes, generated CSS, and project stylesheets from your AI client.
作者のリポジトリから書かれたとおりにコピーしたものです。PopNx MCPは内容を確認・推奨していません。HTML、画像、スクリプトは取り除いています。リンクはこのサイトの外へ移動します。
Control Krita from OpenAI Codex through a secure local Model Context Protocol (MCP) server for Windows and Linux.
PyPI package · GitHub releases · Windows installation guide · Linux installation guide · Codex and MCP compatibility
A local MCP server that lets Codex inspect and control Krita through a small, authenticated bridge. The MCP process uses STDIO. The Krita Python plugin listens only on 127.0.0.1, validates a shared bearer token, and dispatches every Krita API call to Qt's main thread.
Windows is the original supported platform; Linux support is experimental. Both platforms use a capability-based runtime compatibility check. Krita 5.3.2.1 on Windows is a tested build, not a hard version requirement. The server deliberately exposes a small set of cohesive tools instead of a large collection of micro-tools:
| Tool | Purpose |
|---|---|
krita_state | Active document, canvas/color space, recursive layer tree with UUIDs, active layer and current painting state |
krita_preview | Whole-canvas or pixel-precise cropped PNG returned directly as MCP image content |
krita_canvas | Sample colors; resize, scale, crop, rotate or flip; import editable raster layers |
krita_edit | Create/refine/move selections; native copy, cut, paste, selection-to-layer, fill and clear |
krita_document | Inspect runtime compatibility; list, create, open, activate, save and close documents |
krita_layers | Read/edit the layer tree, safely reparent, and transform layers by stable UUID |
krita_history | Read undo/redo state and execute bounded undo or redo steps |
krita_brush | Read/set native brush state and search installed Krita presets |
krita_paint_path | Pressure-aware line segments through Krita's native Node.paintLine API and active brush preset |
krita_draw | Native preset-backed lines, open/closed paths, polygons, rectangles and ellipses |
krita_color | KRA-backed project palettes, Krita palette swatches, color replacement and safe correction filters |
krita_asset | Export layer PNGs plus Unity-oriented animation, tileset and named-region packages with direct previews |
krita_save_export | Save KRA and export PNG beneath configured roots only |
Codex -> local STDIO MCP process -> authenticated 127.0.0.1 HTTP bridge
-> queued, timeout-aware Qt main-thread dispatch -> Krita Python API
The bridge has no arbitrary Python execution tool and no direct pixel painting fallback. Actual painting, shapes, replacement fills and correction filters go through native Krita actions or stroke APIs. If the running Krita build lacks a feature, krita_state and krita_document(action="compatibility") report the affected tools. Calling that feature returns a structured error; the bridge never silently switches to a different rendering backend.
Choose the installation source for your platform:
| Platform | Installation source | Validation |
|---|---|---|
| Windows | PyPI 0.2.2 or a checkout | Windows CI; original live testing with Krita 5.3.2.1 |
| Linux | PyPI 0.2.2 or a checkout | Linux CI; contributor live test on Debian 13 / Krita 5.2.9 in limited mode |
Version 0.2.2 includes the Linux/XDG path and private-configuration fixes. Keep the installer, Krita plugin and Codex server on that same exact version; the marketplace launcher also pins it. Other Linux distributions and Krita builds require their own live preflight.
A first-time setup has two separate parts: the local bridge must be installed and enabled in Krita, then Codex must be connected through either the marketplace plugin or a direct MCP configuration. The codex plugin commands do not install or enable anything in Krita.
Krita must include Python scripting, pass the live compatibility check, and have uv/uvx on PATH. Run the MCP process on the same computer as Krita. Local Codex CLI, IDE and supported desktop clients use local MCP configuration; a hosted ChatGPT web chat cannot connect through this computer's 127.0.0.1 bridge by adding this GitHub repository.
uvx --from "krita-codex-mcp==0.2.2" `
krita-codex-install install ` --allowed-root "C:\Krita Work"
uvx --from "krita-codex-mcp==0.2.2" krita-codex-install check
Ready for productive use. or the explicit limited-mode success message.Close Krita, create a narrow allowed directory and install from PyPI:
mkdir -p "$HOME/krita-codex-work"
uvx --from "krita-codex-mcp==0.2.2" krita-codex-install install --allowed-root "$HOME/krita-codex-work"
Enable Krita Codex Bridge in Krita's Python Plugin Manager, close and reopen Krita, then run:
uvx --from "krita-codex-mcp==0.2.2" krita-codex-install check
Accept compatible or explicitly reported limited mode. Follow the Linux guide's Codex setup for either connection method. The installer uses XDG directories and keeps its token configuration private. No sudo is needed.
The repository includes a public, local-first Codex plugin. It bundles the guided krita-control skill and starts the version-pinned PyPI MCP server through uvx; Krita and the authenticated bridge continue to run only on the user's machine. Run these commands only after the Krita bridge has been installed, enabled, restarted, and checked as described above. They register the GitHub marketplace and install the Codex bundle; they do not modify the Krita installation or enable its Python plugin.
codex plugin marketplace add cyyprezz/krita-codex-mcp
codex plugin add krita-codex-mcp@krita-codex
Start a new Codex task after installation, then verify krita_state and krita_preview. Plugin users should not also add a separate [mcp_servers.krita] block because the plugin already provides that server. For later repository releases, run codex plugin marketplace upgrade krita-codex, rerun codex plugin add krita-codex-mcp@krita-codex, and start another new Codex task.
For either platform, use this alternative only after the Krita bridge has passed the live check. Preview the checkout-free, exactly version-pinned uvx Codex block with krita-codex-install codex-config. Apply it only after explicit confirmation, restart Codex, verify krita_state and krita_preview, and only then start normal work.
Install and update never close Krita. If the authenticated bridge is running, replacement is rejected before any installed files are changed and Krita must be closed manually. A busy local bridge port also stops the installer before replacement begins.
For a personal installation, use the user-level ~/.codex/config.toml on Linux or C:\Users\ \.codex\config.toml on Windows. This is the recommended option because the server is then available to all local Codex tasks and Git worktrees. The generated block uses uvx, has no checkout cwd, and pins the same exact distribution version as the installed plugin. The installer only changes that file after showing the full preview and receiving explicit confirmation. Unmarked or conflicting Krita entries are never overwritten. Never commit personal configuration. See the Windows installation guide for details.
The generated launcher and marketplace configuration explicitly forward custom XDG directories. Codex and Krita must inherit the same values. For unreleased source changes, use the checkout-specific alternative in the Linux guide.
The compatibility check uses Codex CLI 0.163.0 (released 2026-10-15) against the built wheel and checks discovery of all 13 tools without an API key, model request or running Krita. See the compatibility notes for its exact scope.
This server intentionally stays on the MCP Python SDK 1.x maintenance line (mcp<2). Current Codex retains the legacy STDIO handshake used by this SDK. The newer MCP 2026-07-28 protocol and portable plugin format do not by themselves require replacing this working local integration. The existing Codex plugin manifest remains a supported compatibility format; full support for newer MCP protocol features would be a separate, tested SDK migration.
The preflight checks local configuration, the complete installed hash manifest, wheel/plugin/ protocol versions, loopback port, authentication and the running Krita capability profile. The running plugin reports the distribution, protocol and Krita versions without adding an MCP tool. The check creates a disposable document, verifies a new paint layer, native drawing, Undo/Redo, transactional reparenting, direct PNG preview bytes and temporary KRA/PNG output beneath an allowed root. It restores the previously active document and removes every temporary file.
An unknown Krita version is accepted when all critical capabilities pass. Missing optional features produce limited warnings naming the affected MCP tools; missing projection, persistence, stable layer-tree or document-lifecycle APIs remain critical. The same structured report is available to Codex through krita_state, so it can avoid unavailable operations.
The current release supports native preset-backed painting and shapes, persistent document and layer editing, selections, color operations, KRA/PNG output, and Unity-oriented animation, tileset and named-region packages. Preview and asset operations return PNG images directly to the MCP caller. Re-export preserves Unity .meta sidecars for stable generated filenames.
The tested Krita 5.3.2.1 build imposes several safety limits. Other builds are evaluated at runtime and may report different available features:
checkpoint_reopen=true can perform that round trip automatically.Node.paintLine requires integer QPoint values, so incoming canvas coordinates are rounded at the native API boundary.Timeouts are operation-specific across Codex, the MCP BridgeClient, the local HTTP bridge and Qt's main-thread dispatcher:
冒頭だけを表示しています。続きはリポジトリで読めます