Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Descripción del creador (original en inglés)
MCP server for Cinema 4D — entity CRUD, parameter-level access, batched undo, security controls.
Estos tres nunca se combinan en una sola puntuación: las opiniones, las mediciones y la popularidad son cosas distintas.
Todavía no escribimos un resumen sencillo para este. Abajo están los datos que leímos del registro.
Elige la app de IA que usas y copia la configuración.
Necesitas
¿Qué app usas?
Elige tu app arriba. La recordamos, así que la próxima vez el botón dirá “Instalar en …”.
Abre Claude Desktop → Settings → Developer → Edit Config y pega esto en claude_desktop_config.json
{
"mcpServers": {
"cinema4d": {
"command": "npx",
"args": [
"-y",
"@kumoproductions/mcp-cinema4d"
]
}
}
}Ejecuta esto en tu terminal
claude mcp add cinema4d -- npx -y @kumoproductions/mcp-cinema4dPégalo en .cursor/mcp.json de tu proyecto, o en ~/.cursor/mcp.json
{
"mcpServers": {
"cinema4d": {
"command": "npx",
"args": [
"-y",
"@kumoproductions/mcp-cinema4d"
]
}
}
}Tu navegador te pide permiso para abrir la app; luego la app muestra la configuración y te pide confirmar. Los valores de las claves quedan vacíos para que los completes tú.
Pégalo en .vscode/mcp.json de tu proyecto
{
"servers": {
"cinema4d": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@kumoproductions/mcp-cinema4d"
]
}
}
}Tu navegador te pide permiso para abrir la app; luego la app muestra la configuración y te pide confirmar. Los valores de las claves quedan vacíos para que los completes tú.
Este se ejecuta en tu computadora, y ChatGPT solo puede conectarse a servidores en internet. Elige otra app.
Tu elección se guarda en una cookie en este dispositivo; no necesitas cuenta.
Esta configuración se genera a partir de la ficha del creador en el registro. Si el README dice otra cosa, sigue el README.
Se ejecuta en tu computadora; la lista de herramientas aparece en tu app de IA después de instalarlo.
Revisamos información que cualquiera puede ver; no hemos leído el código. Las revisiones que no aplican no se cuentan. · Revisado el 7 nov 2026
El nombre en el registro se verificó con la cuenta de GitHub kumoproductions, dueña del repo
Todavía no hemos leído este repo en GitHub
Todavía no hemos leído este repo en GitHub
Este se ejecuta en tu computadora; no hay endpoint en internet
Se ejecuta en tu computadora y usa ajustes locales en su lugar
Se ejecuta en tu computadora; solo podemos leer listas de herramientas de endpoints en internet
Comparado con todos los servidores activos de esta categoría en el registro. Las estrellas solo cuentan cuando quien lo publica es dueño del repo.
Superó 1 de 1 revisiones básicas aplicables. No hemos leído el código. Antes de agregar una clave o un token, revisa qué acceso pide el servidor y usa una clave que tenga solo los permisos que necesitas.
El registro no indica ninguna clave obligatoria, aunque algunos servidores te piden iniciar sesión la primera vez que los usas.
Se ejecuta en tu computadora. Tu app de IA lo inicia cuando hace falta, y los datos no pasan por los servidores del creador (a menos que el propio servidor llame a un servicio en línea).
El repo de GitHub cambió por última vez –, y la última versión (0.5.1) llegó al registro hace 38 días.
Las apps compatibles con MCP, como Claude Desktop, Claude Code, Cursor y VS Code. También necesitas Node.js en tu computadora.
En la misma categoría: Spec Driven Development, Remote Desktop Commander, Foliosio
Servidores de la misma categoría hechos por otros creadores, ordenados por estrellas.
Cómo leer una tarjeta:★ Estrellas de GitHubiTres pilares: reseñas · revisiones · usoiActualizado = fecha en que se publicó la última versión en el registroi
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.
Read your support inbox, tag conversations and save draft replies from your AI agent. Never sends.
Copiado tal cual del repo del creador. PopNx MCP no lo ha revisado ni lo respalda. Se quitaron HTML, imágenes y scripts. Los enlaces llevan fuera de este sitio.
Let an LLM drive Cinema 4D. mcp-cinema4d bridges MCP-compatible clients (Claude Desktop, Claude Code, or any other stdio-capable MCP client) to a running Cinema 4D 2026 session so the model can inspect scene hierarchy, author shots, build node materials, and rig animation through a typed, undo-safe tool layer — not arbitrary Python pasted into a Script Manager.
日本語
简体中文
[!IMPORTANT]
Cinema 4D now ships an official MCP server. From Cinema 4D 2026.4, Maxon builds an MCP server into Cinema 4D itself: nothing to install, set up from Preferences → MCP, and supported by Maxon. If you run 2026.4 or later and simply want an AI assistant in Cinema 4D, start there — see Maxon's MCP Server page and documentation.
mcp-cinema4d is an independent community project. It remains an option where the built-in server does not fit:
- Cinema 4D 2026.0–2026.3, which have no built-in server.
- Several Cinema 4D processes from one session (multi-instance mode), which the built-in server's documentation does not cover.
- Open source — read, audit, or extend the tools and the bridge yourself.
Do not register both servers in the same client. Their tool sets overlap (both expose
exec_python, for example), so the model is offered two competing sets of Cinema 4D tools. Maxon's FAQ likewise asks you to switch third-party servers off while you use the built-in one.
Good for:
hero layer; flag any with non-uniform scale or missing Texture tags."[!CAUTION]
Do not proceed unless you understand what this does. An LLM with a live connection to Cinema 4D can read your scene, write to it, and (if you opt in) execute arbitrary code on your machine. In concrete terms:
1. Your scene data leaves your machine. Object names, hierarchy paths, material/parameter values, imported file paths — whatever the LLM reads via
list_entities/describe/get_container/dump_shader/get_mesh— is forwarded to your chosen LLM provider and may be logged by your MCP client. Under NDA or on unreleased IP? Confirm with your studio/legal team first that the provider's retention policy and your client's logs are acceptable.
2. The LLM gets write access. It can create, mutate, and delete objects, tags, materials, takes, render data, and layers; import / merge / open / save files; and render. Ctrl/Cmd-Z covers most edits —
save_document,open_document,render, and somecall_commandinvocations do not.
3. Arbitrary Python is off by default.
exec_pythonruns unrestricted code with the full authority of the Cinema 4D process (file I/O, subprocess, network). Enabled only whenC4D_MCP_ENABLE_EXEC_PYTHON=1is set on both sides; turn it back off when you no longer need it. The same applies to plugin types that store Python source in their container — Python tag, Python generator, MoGraph Python effector, Python field, and the Xpresso Python operator. Creating or editing them is gated behind a separateC4D_MCP_ENABLE_PYTHON_OPS=1opt-in, since their code parameter is RCE-equivalent toexec_python.
Before first use: back up (or commit) your scene, start on a throwaway project, and leave your MCP client's per-call approval prompts enabled. See Security before exposing the bridge beyond loopback.
MCP client
↓ stdio MCP server (this repo, Node.js) ↓ TCP, JSON Lines (default 127.0.0.1:18710) cinema4d_mcp_bridge (Python plugin inside C4D) ↓ Cinema 4D
Two pieces to install: the MCP server (this npm package, runs as an MCP stdio process) and the bridge plugin (Python, lives inside Cinema 4D). C4D must be running for the bridge to respond.
Assuming you already have Cinema 4D 2026.0.0+ and Node.js 24+.
cinema4d_mcp_bridge- .zip from the Releases page and extract the cinema4d_mcp_bridge/ folder into your Cinema 4D plugins directory (see Installing the bridge plugin for platform-specific paths).[cinema4d_mcp_bridge] listening on 127.0.0.1:18710. echo '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"ping","arguments":{}}}' \
| npx -y @kumoproductions/mcp-cinema4d
Then wire it into your MCP client (see Client configuration) and try:
_"List every object in the scene, then add a cube named
hero200 units above the origin."_
The LLM will call list_entities → create_entity in sequence; you should see a new cube appear in the viewport.
Prefer running from a local checkout? See CONTRIBUTING.md for the source-install flow.
Generate a random token and set it on both the MCP server process (via the client's env map, below) and the Cinema 4D launch environment. The bridge rejects mismatched requests (constant-time compare); the Node client forwards the value automatically. Strongly recommended — localhost is not a trust boundary on a shared workstation.
openssl rand -hex 16
Register the MCP server in your client with the token in the env map:
{
"mcpServers": { "cinema4d": { "command": "npx", "args": ["-y", "@kumoproductions/mcp-cinema4d"], "env": { "C4D_MCP_TOKEN": "paste-your-random-hex-here" } } } }
| Client | Config file |
|---|---|
| Claude Desktop / Claude Code | %APPDATA%\Claude\claude_desktop_config.json (Windows) · ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) |
| Other MCP clients | see the client's docs for registering a stdio server |
**The same C4D_MCP_* variables must also be set in the Cinema 4D launch environment** — the bridge plugin reads them at C4D startup. macOS: open -a "Cinema 4D" --env C4D_MCP_TOKEN=... (or export in your shell profile before launch). Windows: set as User environment variables and restart C4D.
To change the bridge socket, set C4D_MCP_PORT (and optionally C4D_MCP_HOST — see Security) alongside C4D_MCP_TOKEN in the same env map, plus the C4D launch env.
72 tools across 17 groups. The LLM picks tools itself based on the prompt — you rarely invoke them directly. See docs/TOOLS.md for the full table with per-tool descriptions.
| Group | Count | What's in it |
|---|---|---|
| Basics | 4 | ping, render, preview_render (Viewport renderer + Constant Lines, returns inline PNG), reset_scene. |
| Script-style | 5 | exec_python (opt-in), call_command, list_plugins, undo, batch — escape hatches + undo-grouped multi-op. |
| Generic CRUD | 9 | list_entities, describe, get_params/set_params, get_container, dump_shader, create_entity, remove_entity, set_keyframe. |
| Shot setup | 11 | Document state, fps / frame range / camera, import_scene (merge), RenderData + Take, take_override, timeline markers (create_marker / list_markers / set_marker / remove_marker), sample_transform. |
| Selection · Hierarchy | 4 | Active selection read / write; reparent, reorder, clone. |
| Modeling · Mesh | 4 | modeling_command (CSO / Make Editable / Connect / Subdivide / …), get_mesh, set_mesh, set_mesh_selection. |
| Document I/O | 6 | save_document, open_document, new_document, list_documents, set_active_document (switch between already-open docs), close_document (force-gated for unsaved changes). |
| Node graphs | 10 | Node-material graphs (walk / asset enum / apply_graph_description / per-port edits / removal) and Xpresso (GvNodeMaster) graphs (list_xpresso_nodes / apply_xpresso_graph / set_xpresso_port / remove_xpresso_node). |
| Tag helpers · Animation | 5 | assign_material; list_tracks, get_keyframes, delete_keyframe, delete_track. |
| Transforms · User data · MoGraph | 5 | set_transform; add_user_data / list_user_data / remove_user_data; list_mograph_clones. |
| Layers | 5 | Enumerate, create, assign, query, flag toggles (solo / view / render / locked / …).
Solo se muestra el principio; lee el resto en el repo