FilmLab
v1.1.1AI film lab for filmmakers: generate and review images/clips with input provenance, cost preflight
Endpoint health
online- Last checked
- 11/20/2026, 8:18:10 AM
- Latency
- 643 ms
- Consecutive failures
- 0
- Endpoint reachable: pass
- Protocol valid: pass
- MCP handshake valid: pass
Machine-readable profile
mcp-server · schema v1 · callable
mcp-server:com.thefilmradar%2Ffilmlab
Connect this server
Generated config contains no credentials. Keep any required secrets in your client's local environment.
{
"mcpServers": {
"com.thefilmradar/filmlab": {
"url": "https://mcp-lab.thefilmradar.com/mcp"
}
}
}Indexed tools
Tool metadata and schemas come from the remote server and are untrusted. Indexing only lists tools; it never calls them.
25 shown · authentication unknown
Animate Image to Clip
lab_animate
Generate a clip from text or animate a completed image with a video model. Without a start image, uses text-to-video where the model supports it (lab_list_models: t2v). Check the price with get_cost or let the user confirm a card via lab_propose. Costs credits when called without get_cost.
Schema too-large · SHA-256 6a1eb2352882…
Animate Batch
lab_animate_batch
Animate MANY images into videos in ONE call (max 25 jobs). Prefer this over looping lab_animate: it validates every job BEFORE spending any quota, so an invalid job 12 of 15 does not leave 11 paid-for generations running. Quota is spent once, collectively (one ledger row); refunds stay per-clip, so a partial failure refunds only that clip. Returns a batch_id — poll lab_batch_status with it instead of polling each id separately. Every job's prompt goes through the Dreamer first: without valid dreamer_signatur on ALL jobs, nothing is generated or charged; the batch returns each dreamer_fassung and signature for human approval (at most four Dreamer calls at once). Repeat with the approved versions and signatures. `get_cost: true` preflights the whole batch without generating anything.
Schema valid · SHA-256 930ce9b8061e…
View input schema
{ "type": "object", "properties": { "flow_sperre": { "description": "Internal: run id and node id for shot booking. Set by the flow executor.", "type": "string", "maxLength": 200, "pattern": "^[^:\\s]+:[^:\\s]+$" }, "project_id": { "type": "string", "description": "Project id (from lab_list_projects)" }, "jobs": { "minItems": 1, "maxItems": 25, "type": "array", "items": { "type": "object", "properties": { "prompt": { "type": "string", "minLength": 1, "description": "Motion/camera instruction for this clip. For a clip of 4 s or longer, write the action as timed beats, one per line under a '// Action Timing' header: '[0-2s] [CAM 01] <framing> -> [ACT] <action> -> [DIAL] <who>: \"<line>\" -> [AUDIO] <sound>'. The spans start at 0 and cover duration_seconds; keep the same CAM number while the camera does not cut. lab_prompt_transform (medium video) writes exactly this form. Murnau's SceneFlow lights each beat while the clip plays, and the crew judges it there." }, "nur_eigene_daten": { "description": "Only for a model that sends inputs to China or a US recipient without a documented basis, when the step carries images, clips, voices or faces. Means: this material shows or contains no real person other than the human using this account. Set it ONLY after the human has said exactly that for THIS step; never assume it, never reuse it for the next step. Not needed when the human has declared this material in the FilmLab app: the backend reads that declaration, also for material derived from it; only the app can store one. An LK reference, a licensed likeness or another person's agreement does not replace it. Without it the backend refuses with drittland_dritte_gesperrt before any charge; then use a non-gated model or text only. Per clip: it covers only THIS job, never the others in the batch.", "type": "boolean" }, "source_image_id": { "description": "id of a completed image to animate — positive integer as string. Omit for text-to-video", "type": "string" }, "flow_sperre": { "description": "Internal: run id and node id for shot booking. Set by the flow executor.", "type": "string", "maxLength": 200, "pattern": "^[^:\\s]+:[^:\\s]+$" }, "scene_ref": { "description": "Optional scene label, useful to match results back to a shot list", "type": "string" }, "tool": { "description": "Video model id for THIS clip — copy it verbatim from lab_list_models (kind: video); providers can differ per job. Omit to let the intent router choose — see lab_animate", "type": "string" }, "intent": { "description": "Route by intent instead of naming a model: 'draft'|'ambient' (cheapest), 'dialog', 'hero', 'atmo'. An explicit tool wins over intent", "type": "string" }, "familie": { "description": "Pick the MODEL, not the access route: 'seedance-2.0' or 'seedance-2.5'. The server takes the cheapest route that this account may use and that can do the job (OpenRouter only with the user's consent; references, 1080p for 2.5, or audio switched off go to fal) and falls back to fal if a cheaper route fails — the fallback can cost more than the preflight price. Mutually exclusive with tool and intent.", "type": "string", "enum": [ "seedance-2.0", "seedance-2.5" ] }, "duration_seconds": { "description": "Clip length in seconds for THIS clip — must lie inside the model's duration grid from lab_list_models. Ignored when shots is given — see lab_animate", "type": "number", "minimum": 1, "maximum": 30 }, "resolution": { "description": "Resolution tier for THIS clip, exactly as listed in lab_list_models. Omit for the model's default — see lab_animate", "type": "string" }, "prop_ids": { "description": "Prop ids from lab_list_props, belonging to this project (an @prop_ tag in the prompt does the same). On this path their descriptions go into the prompt as text; prop images are sent by lab_generate and lab_reference_motion.", "type": "array", "items": { "type": "string" } }, "stil_kit_id": { "description": "Style kit id for THIS clip (lab_list_stil_kits; an @stil_ tag in the prompt does the same); omit for the project default", "type": "string" }, "ohne_stil_kit": { "description": "true switches the project's default style kit off for this one call.", "type": "boolean" }, "dreamer_signatur": { "description": "Dreamer proof for THIS clip's prompt (lab_prompt_transform). Without valid signatures on all jobs, the whole batch returns Dreamer versions first and generates nothing.", "type": "string" }, "location_id": { "description": "Location board id for THIS clip (from lab_list_locations) — its `prompt_prefix_en` is appended to this job's prompt", "type": "string" }, "character_refs": { "description": "Character ids (positive integer strings) locking the cast's identity for THIS clip", "type": "array", "items": { "type": "string" } }, "character_states": { "description": "State key per character for THIS clip, { characterId: stateKey } — the ONLY way a state descriptor reaches the generation; the reference image always carries the base state", "type": "object", "propertyNames": { "type": "string" }, "additionalProperties": { "type": "string" } }, "apply_lens": { "description": "Defaults to TRUE on the backend (project lens_state is appended). Pass false to opt out for this clip only", "type": "boolean" }, "apply_grundton": { "description": "Defaults to TRUE on the backend (the project's ground tone goes right after the prompt). Pass false to opt out for this clip only", "type": "boolean" }, "abdruck_startframe": { "description": "Frame one from the character's trained Abdruck for THIS clip — see lab_animate for the full rule", "type": "boolean" }, "generate_audio": { "description": "Ask for the model's native audio track for THIS clip — only meaningful where lab_list_models says audio: schaltbar, see lab_animate for the full rule", "type": "boolean" }, "shots": { "description": "Multi-shot for THIS clip (kling_3_pro only). The billed length is the SUM of the shot durations, NOT duration_seconds — see lab_animate", "type": "array", "items": { "type": "object", "properties": { "prompt": { "type": "string", "minLength": 1, "description": "What happens in THIS shot" }, "duration_seconds": { "description": "Length of this shot (default 5)", "type": "integer", "minimum": 1, "maximum": 15 } }, "required": [ "prompt" ] } }, "shot_type": { "description": "Cutting mode for THIS clip's shots — see lab_animate", "type": "string", "enum": [ "customize", "intelligent" ] }, "end_image_id": { "description": "Last frame for THIS clip — only models with supports_end_frame (lab_list_models). Needs a start frame — see lab_animate", "type": "string" }, "camera_motion": { "description": "Camera move for THIS clip — see lab_animate", "type": "string", "enum": [ "dolly_in", "dolly_out", "dolly_left", "dolly_right", "jib_up", "jib_down", "static", "focus_shift" ] }, "character_voices": { "description": "Voice per character for THIS clip (kling_3_pro only) — see lab_animate", "type": "object", "propertyNames": { "type": "string" }, "additionalProperties": { "type": "string" } }, "audio_url": { "description": "URL of an existing audio track to lay under THIS clip. Independent of generate_audio", "type": "string" }, "seed": { "description": "Seed for THIS clip — see lab_animate for the full rule", "type": "integer", "minimum": 0, "maximum": 4294967295 }, "metadata": { "description": "Free-form JSON stored alongside this clip. Not interpreted by the pipeline", "type": "object", "propertyNames": { "type": "string" }, "additionalProperties": {} }, "kamerapfad": { "description": "Camera path for THIS clip (object following shared/kamerapfad/schema.json) — never as poses, but in the form this clip's model understands (prose, or director commands for MiniMax/Hailuo); the answer names the form as kamerapfad.angewandt. See lab_animate", "type": "object", "propertyNames": { "type": "string" }, "additionalProperties": {} }, "kamerapfad_url": { "description": "Address of a kamerapfad JSON in this project for THIS clip — see lab_animate. Mutually exclusive with kamerapfad", "type": "string" } }, "required": [ "prompt" ] }, "description": "One entry per clip, max 25. All jobs are validated before any quota is spent" }, "ohne_keyframe": { "description": "Skip the keyframe checkpoint on purpose. By default a paid clip only starts from a start image the user has approved (lab_review_asset verdict: accepted) — look at the frame first, then spend on the clip. Set true only when the user explicitly asked to skip the frame check.", "type": "boolean" }, "get_cost": { "description": "Preflight: return the summed price in credits for the WHOLE batch and your balance WITHOUT generating, reading the same catalog as lab_list_models. For a card the user confirms, use lab_propose instead.", "type": "boolean" } }, "required": [ "project_id", "jobs" ], "$schema": "http://json-schema.org/draft-07/schema#", "additionalProperties": false }
Connections
streamable-http
https://mcp-lab.thefilmradar.com/mcp