Skip to main content
Glama
joeshwoa

omnicinema-mcp

by joeshwoa
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

Make a Short Video (screenplay → footage → edit → MP4)

run_cinema_pipeline

Turn a one-line idea into a multi-scene video with screenplay, stock or storyboard shots, narration, soundtrack, and an MP4 render; dry-run first to preview plan and cost.

Instructions

Use when the user wants a short video from a one-line idea. Writes a multi-scene screenplay with shot-to-shot continuity, fills each shot with stock footage (Pexels/Pixabay/Unsplash, only if their keys are set) or an offline storyboard frame, optionally adds narration (offline system TTS + captions) and a soundtrack fitted to the cut, edits a frame-accurate timeline (hard cuts in a scene, dissolves between scenes) and renders an MP4 with Remotion or ffmpeg. TIP: call with dry_run:true first — it returns the screenplay, shot list, provider choice and a cost/network estimate instantly without writing files, so you can show the user before producing. Network/money: stock APIs are used automatically when keys exist (free; set stock:false to stay offline). generative:true calls paid-or-quota video APIs (budget-guarded; approveOverBudget:true to exceed). With no keys everything runs offline. Returns: projectId, rendered MP4 path (if rendered), screenplay.md, timeline.json, attributions, warnings, next steps. interactive_montage pauses before the edit so a human can reorder/replace clips, then compile_montage finishes.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
fpsNoFrames per second (default 30).
stockNoUse stock APIs when keys are configured (default true). false = fully offline storyboard/animatic.
styleNoVisual style, e.g. 'noir', 'documentary', 'neon cyberpunk'. Also steers lighting.
widthNoFrame width (default 1920). Use 1080 with height 1920 for vertical.
enrichNoSPENDS MONEY: true + ANTHROPIC_API_KEY polishes the screenplay prose with one Anthropic API call. Default false (offline template prose).
heightNoFrame height (default 1080).
preferNoPrefer motion b-roll ('video', default) or stills ('image') from stock.
promptYesThe video idea, e.g. 'a lone lighthouse keeper watching a storm roll in'.
renderNoRender the MP4 now (default true in fully_automated). Uses Remotion if installed, else ffmpeg.
dry_runNotrue = plan only: screenplay, shot list, providers, cost estimate. No files, no network, no quota.
captionsNoBurn narration captions into the video (default true).
narrationNoNarration script. Spoken offline by the system TTS (say/flite/espeak-ng), captioned, locked to the timeline; the last shot is held if the narration runs long.
generativeNoSPENDS QUOTA/MONEY: generate clips with your Replicate/fal/HF video model (default false).
musicStyleNoSoundtrack genre: 'lo-fi', 'cinematic orchestral', 'hip-hop', 'trap', 'rock', 'electronic', 'ambient'.
sceneCountNoNumber of scenes (default 3–5 from the prompt). Scenes follow a story arc.
soundtrackNoAdd an offline-synthesized soundtrack fitted to the video length, ducked under narration.
shotsPerSceneNoShots per scene (default 2): establishing → medium → close.
workflow_modeNofully_automated renders in one call; interactive_montage stops after gathering clips (then use compile_montage).fully_automated
approveOverBudgetNoOnly after the user agrees: proceed past the free-tier budget guard.
shotDurationSecondsNoSeconds per shot (default 4).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.3.0

TDQS

A4.8/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden and does so well: it discloses that stock APIs only engage when keys exist, that everything runs offline otherwise, that generative:true spends money/quota behind a budget guard, and that approveOverBudget must be user-approved. It also enumerates the return payload and the warnings category.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loads the trigger, then the TIP, then cost/network caveats, then returns — a sensible priority order. It is dense and a little long, but each block (usage, tip, cost, returns) earns its place for a 20-parameter tool.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 20-parameter, no-output-schema tool, the description covers the essentials an agent needs: the trigger, the cost/network decision tree, the offline fallback, the interactive versus automated paths, and the explicit return fields. Nothing critical is left to inference.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, but the description still adds meaning: it explains the dry_run shortcut, the cost implications of generative/enrich, the stock:false offline mode, and the interactive_montage handoff. It does not contradict or merely restate the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource+output: produces a short video from a one-line idea via screenplay, footage, edit, and MP4 render. It names the sibling relationship (interactive_montage pauses, then compile_montage finishes), so an agent can distinguish it from generate_image or generate_voiceover in the same family.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Opens with an explicit trigger ('Use when the user wants a short video from a one-line idea') and adds an actionable TIP to call with dry_run:true first to show the plan before producing. It also routes the agent between workflow_mode values and names compile_montage as the follow-up tool.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

Other Tools