studio-mcp
This server provides an LLM agent-driven pipeline for film production, managing everything from initial planning and look development to rendering, quality control, and final assembly. It offers 14 tools across these areas:
Plan & Lock
plan_shots: Convert a plain-language brief into a structured shot plan (type, move, duration, action, etc.)lock_campaign: Define and lock the campaign's visual style (aspect ratio, film stock, color palette, elements, audio rules) for consistency across shotspalette_from_image: Extract a HEX palette from a moodboard or stillreference_prompt: Deconstruct a reference image into a ready-to-use prompt
Generate & QC
gen_still: Generate a still image using a 6-layer promptqc_still: Automated style-drift QC scoring intent, look, and character (0–100) with a pass/fail verdict and fix suggestionanimate: Convert a still to video (img2vid) with optional direction or hero prompttrain_character: Create a character model from 3–5 photosupscale: Final-polish upscaling for images or video
Assemble & Utility
assemble: Build a cut manifest (shot order, durations, audio notes)cut: Concatenate rendered clips into a single mp4 via ffmpeglist_models: List available image/video models for routingproject_status: Report which pipeline stages (plan/lock/QC/manifest) are complete for a project
Grounded Knowledge
craft_lookup: Query a cited craft knowledge base for expert advice on stocks, lenses, lighting, and prompt structure
The server is LLM-provider agnostic (any OpenAI-compatible endpoint) and can be driven via direct tool calls, a web-based grading bay console, or an orchestration graph with retries and human gates.
Enables the MCP server to use OpenAI's models as the LLM backend for planning, QC, and assembly tools.
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., "@studio-mcp Plan 5 shots for a coastal slow-burn film project 'MARÉA'"
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.
studio-mcp
The block-method film pipeline as agent-callable MCP tools.
An MCP server that lets an LLM agent drive a full brief → shots → render → QC → cut
workflow by calling tools — instead of clicking through generation UIs by hand.
Plan-then-generate, never reverse: every shot is planned (type, move, duration)
before any pixel is made, and every still is QC'd against a locked look so the
piece stays on-model.

Above: one shot from the brief "MARÉA — wordless coastal slow-burn" — planned, rendered on Higgsfield Soul Cinema at 21:9, and passed by the style-drift QC (intent 80 / look 84 / character 90). The agent re-rolls anything that fails.
Why
Single-tool MCP servers (one model, one call) are common. This is the layer above: it orchestrates across your generation stack with a block-method planner and a style-drift QC gate — the part nobody ships.
Related MCP server: StoryboardStudio MCP
Three ways to drive it
As an MCP server — connect to Claude Desktop / Claude Code and the LLM calls the 14 tools directly (stdio, or
--transport streamable-httpfor web clients).The web console — a cinematic "grading bay" UI over the server: browse instruments, invoke them from schema-driven forms, stream long renders, and brief the Director (an LLM that drives the instruments for you). Live demo: https://console-pied-eight.vercel.app ·
console/.The orchestration graph — Planner → Generation ⇄ QC → Assembly as an agent graph with retries, human gates, and replayable per-run traces (
studio_mcp/orchestration/).
Plus Langfuse tracing + an offline benchmark suite for evaluating the pipeline
(eval/). CI runs tests on 3.10–3.12 and builds the package on every push.
Tools (14)
Plan & lock
Tool | What it does |
| brief → block-method shot plan (type · move · duration · lighting · lens · time · hold · vibe) |
| lock the look once — every shot's prompt inherits it |
| extract a HEX palette (dominant/secondary/accent) from a moodboard/still |
| break a reference image into a ready 6-layer prompt (build from a ref) |
Render & QC (via Higgsfield CLI)
Tool | What it does |
| 6-layer Soul prompt → render; |
| vision style-drift QC vs shot intent + lock; pass/fail + fix_suggestion |
| img2vid — |
| soul-id self-clone from 3–5 photos |
| final-polish image/video upscale |
Assemble & utility
Tool | What it does |
| ffmpeg-concat the rendered clips into one |
| cut manifest — order, durations, diegetic-audio notes |
| list available image/video models so an agent can route per shot |
| what stages exist for a project |
Ground (via creative-rag)
Tool | What it does |
| query the craft knowledge base for a grounded, cited, verified answer (stocks/lenses/lighting/prompt structure) — use while planning/locking so prompts trace to the real library, not generic guesses. Needs creative-rag running ( |
Integration — the studio trio
studio-mcp is one of three interlocking pieces; see INTEGRATION.md.
ai-content-pipelineskill — the method (block plan → lock → stills → animate → cut). It maps each stage to the studio-mcp tool that executes it and callscraft_lookupto ground prompts.studio-mcp (this repo) — the tools that execute the method.
creative-rag — the cited craft KB behind
craft_lookup.
Smoke-test the full chain (skill method → craft_lookup → creative-rag):
python scripts/smoke_chain.py # needs creative-rag on :8000Provider-agnostic
The LLM layer talks to any OpenAI-compatible endpoint — Anthropic, OpenRouter, OpenAI, or a local server — chosen entirely through env config. No provider is hard-coded.
cp .env.example .env # set STUDIO_LLM_BASE_URL / _MODEL / _API_KEYInstall
python3 -m venv .venv && source .venv/bin/activate
pip install -e .Run
studio-mcp # stdio MCP serverRegister with an MCP client (e.g. Claude Code / Claude Desktop):
{
"mcpServers": {
"studio": {
"command": "/path/to/studio-mcp/.venv/bin/studio-mcp",
"env": { "STUDIO_LLM_API_KEY": "sk-..." }
}
}
}Example flow
plan_shots("MARÉA — wordless coastal slow-burn, 90s", project="marea")
lock_campaign("marea", aspect="21:9", day_stock="Kodak 500T, soft handheld",
hex_palette=["#1b2a3a","#c8a15a"], elements=["the woman in grey"],
audio="diegetic SFX only, no music")
# render a still (v1.1) → then:
qc_still("marea", image="assets/shot1.png", shot_id=1) # pass/fail + fix
assemble("marea") # cut manifestState lives under STUDIO_ROOT (default ~/studio-projects/<project>/) as plain
JSON — human-inspectable, and a clean contract a future console can read.
License
MIT
Available Tools
5 toolsassembleA
Build the cut manifest — shot order, durations, and audio notes.
Uses the plan for order/timing. If clips (e.g. [{"shot_id":1,"path":"..."}]) are provided (v1.1+), they are attached per shot. The actual NLE cut stays manual in v1; this is the edit blueprint.
Args: project: project name. clips: optional rendered-clip refs keyed by shot_id.
Inputs: project (required), clips.
lock_campaignA
Lock the campaign look so every shot stays on-model.
Args: project: project name. aspect: aspect ratio, e.g. "2.39:1" or "9:16". stock: film stock / look, e.g. "Kodak Vision3 500T, soft handheld". hex_palette: HEX colors defining the palette, e.g. ["#1b2a3a", "#c8a15a"]. elements: recurring elements/characters to keep consistent. audio: audio rule (default: diegetic SFX, no music).
Inputs: project (required), aspect (required), stock (required), hex_palette (required), +2 more.
plan_shotsA
Turn a brief into a structured block-method shot plan.
Plans every shot (type, camera move, duration, action) before any pixel is generated. Saves to the project's plan.json and returns it.
Args: brief: plain-language description of the spot/scene. project: project name (scopes all state, e.g. "marea"). n_shots: target number of shots.
Inputs: brief (required), project (required), n_shots.
project_statusA
Report what stages exist for a project (plan / lock / QC / manifest).
Inputs: project (required).
qc_stillA
Style-drift QC on a generated still against the shot intent + locked look.
Vision model scores intent / look / character (0-100). Pass requires every score >= threshold. Saves the verdict and returns it. An agent re-rolls the still when pass is false, using fix_suggestion.
Args: project: project name. image: local path or http URL of the still to review. shot_id: which shot in plan.json this still is for. threshold: minimum passing score per dimension.
Inputs: project (required), image (required), shot_id (required), threshold.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 5 tools
Each tool has a distinct purpose: assemble builds the cut manifest, lock_campaign sets the visual look, plan_shots creates the shot plan, project_status reports stage completion, and qc_still performs quality control. There is no overlap or ambiguity between them.
Tool names are not perfectly consistent: 'assemble' is a bare verb, while others follow verb_noun (lock_campaign, plan_shots) or noun_noun (project_status) patterns, and 'qc_still' uses an abbreviation. The naming is understandable but lacks a uniform convention.
With 5 tools, the count is appropriate for the domain of film production planning and quality control. It covers the main workflow stages without being too heavy or too sparse, though a few more specialized tools could be added later.
The tool set covers the core stages: planning, look locking, assembly, QC, and status tracking. Notable gaps like actual rendering or exporting are intentionally omitted per v1 scope. The surface is fairly complete for its intended purpose.
Maintenance
Related MCP Connectors
Agentic AI video editor: edit a real timeline, generate clips, music and voice, then render.
Make AI short films with your agent: script, storyboard, quoted image and video, review and export.
AI video editor your agent can drive: plan scenes, edit a multi-track timeline, and render MP4s.
Video, image and audio generation on top AI models for agents, with an AI director built in.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceEnables AI coding agents to generate cinematic video and image assets and perform autonomous timeline assembly, multi-track audio editing, chroma-key compositing, and local draft manipulation from conversational prompts.3MIT
- AlicenseNot gradedqualityCmaintenanceEnables LLM agents to generate and validate multi-granularity storyboard assets from text prompts, including 2D SVG motion, 3D Blender depth/blockout, and SDXL ControlNet final images. It also supports vision-based self-correction and a SQLite knowledge database of successful recipes.MIT
- FlicenseNot gradedqualityBmaintenanceEnables a local LLM to direct Unreal Engine 5 scenes through verified task-level macros and bounded workflows, applying character animations, measuring poses and foot placement, and capturing evidence while restoring state on failure. It also supports plain-language orders for character actions, crowds, and reference-video generation without requiring a small model to compose hundreds of atomic engine tools.1-
- FlicenseNot gradedqualityAmaintenanceEnables an AI agent to ingest raw video clips, plan and edit a montage from natural-language prompts, and produce a rendered, beat-synced cut with matched music, subtitles, transitions, and picture-in-picture.-