Skip to main content
Glama
Sign In

FilmLab

by com.thefilmradar
OverviewDiscussionsAdmin

Apply Timeline Manifest

lab_timeline_apply
Idempotent

Write a WHOLE cut into a sequence in one call — clips in order with their lengths, an optional dissolve between them, an optional bed underneath. This is the counterpart to lab_get_sequence: that one reads the timeline, this one writes it. Prefer it over a chain of lab_add_clip calls whenever you already know the whole cut: a chain that breaks in the middle leaves half a sequence behind, this either applies or refuses. Costs nothing — it validates and writes rows, it generates nothing. Every video_id is checked against the project BEFORE anything is written, so a wrong id is a refusal here and not a gap in the cut nobody notices. Pass sequence_id to write into THAT sequence; omit it and a new one is created. Pass sequence_id WITHOUT a manifest to read back the stored cut as a manifest — for an agent that already has the sequence_id and wants to see what is in there before changing it. (The Resolve bridge does NOT go through here: it talks to the FilmLab server directly with its own bridge key and does not know this MCP.) Reworking a cut you read back? Keep each clip's clip_id. A clip that comes back with its identity keeps its track, its in-point in the source and its scene, and the shots bound to it stay bound; a clip without one is treated as new and gets a fresh identity, which orphans whatever pointed at the old one. Speed per clip: tempo (fixed, 0.0625–16) or tempo_kurve (a ramp in timeline seconds, which wins over tempo); read-back returns them the same way, and nothing is charged for either. Two honest limits: the Resolve bridge applies the clips but reports uebergang and the bed's level/fade as not applied (its scripting API has neither a transition call nor a clip volume property). The FilmLab sequence render applies the bed with its level and fade, but NOT uebergang yet — dissolves are stored and render as hard cuts (checked 2026-10-03).

Input Schema

NameRequiredDescriptionDefault
titleNoTitle for the sequence created when `sequence_id` is omitted
manifestNoThe cut as one object. Omit it only together with a `sequence_id`, to read back what is stored
project_idYesProject id (from lab_list_projects) — positive integer as string
sequence_idNoSequence to write into (from lab_create_sequence/lab_list_sequences). Omit to create a new one. Given WITHOUT a manifest, the stored manifest is read back instead of written
erwartete_revisionNoThe `revision` you read (from lab_get_sequence or this tool's read-back). The cut is written only if the sequence still has exactly that content — otherwise nothing is written and you get `revision_veraltet` with the current revision: read again, merge, write again. Without it this tool still protects the moment between its own read and write, but not the time since YOU read the sequence.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • addedInput schema / properties / manifest / properties / clips / items / properties / tempo
      Added value: +{
+  "description": "Fixed speed of this clip: 1 = normal, 2 = twice as fast, 0.5 = slow motion. The clip keeps its length on the timeline and shows dauer_s × tempo seconds of its source. Setting it removes a ramp the clip had. Ignored (and reported) when a non-empty tempo_kurve is given. Omit both to keep what an existing clip_id has",
+  "maximum": 16,
+  "minimum": 0.0625,
+  "type": "number"
+}
    • addedInput schema / properties / manifest / properties / clips / items / properties / tempo_kurve
      Added value: +{
+  "description": "Speed ramp across the clip — takes precedence over tempo. Needs dauer_s. [] removes a ramp (the clip keeps its average speed; add tempo: 1 for normal). Sound is muted wherever the speed is below 0.5× or above 4×, as in the editor and the export",
+  "items": {
+    "properties": {
+      "kurve": {
+        "description": "Shape from this point to the next: linear, ease (smooth) or halt (hold this speed). Default linear",
+        "enum": [
+          "linear",
+          "ease",
+          "halt"
+        ],
+        "type": "string"
+      },
+      "t": {
+        "description": "Seconds from the clip start ON THE TIMELINE (output time), not in the source",
+        "minimum": 0,
+        "type": "number"
+      },
+      "wert": {
+        "description": "Speed at this point",
+        "maximum": 16,
+        "minimum": 0.0625,
+        "type": "number"
+      }
+    },
+    "required": [
+      "t",
+      "wert"
+    ],
+    "type": "object"
+  },
+  "maxItems": 32,
+  "type": "array"
+}
  2. Changed1 schema field changed
    • addedInput schema / additionalProperties
      Added value: +false
  3. Changed4 schema fields changed
    • addedInput schema / properties / manifest / properties / bett / properties / asset_key
      Added value: +{
+  "description": "Storage key of an audio file in this project (from lab_add_media or lab_list_assets). Stable — prefer it over a URL: the URLs lab_list_assets hands out are signed and expire after 24 h",
+  "type": "string"
+}
    • changedInput schema / properties / manifest / properties / bett / properties / audio_id / description
      Previous value: -"Id of an audio row in this project (from lab_list_audio). Either this or url"New value: +"Id of an audio row in this project (from lab_list_audio). One of audio_id, asset_key, url"
    • changedInput schema / properties / manifest / properties / bett / properties / url / description
      Previous value: -"Direct URL of the bed. Either this or audio_id"New value: +"Direct URL of the bed (external). A signed FilmLab asset URL is turned into its storage key, so it does not expire inside the sequence"
    • changedInput schema / properties / manifest / properties / uebergang / description
      Previous value: -"One transition kind between ALL clips. Stored on the sequence; the Resolve bridge cannot apply it"New value: +"One transition kind between ALL clips. Stored on the sequence — but neither the Resolve bridge nor the FilmLab render applies it yet: the cut renders with hard cuts"
  4. Changed1 schema field changed
    • addedInput schema / properties / erwartete_revision
      Added value: +{
+  "description": "The `revision` you read (from lab_get_sequence or this tool's read-back). The cut is written only if the sequence still has exactly that content — otherwise nothing is written and you get `revision_veraltet` with the current revision: read again, merge, write again. Without it this tool still protects the moment between its own read and write, but not the time since YOU read the sequence.",
+  "maxLength": 64,
+  "type": "string"
+}
  5. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Beyond the annotations, it discloses important behavior: the write validates all video_id values before writing, applies atomically or refuses, costs nothing, and supports optimistic concurrency via erwartete_revision. It also names concrete downstream limitations for the Resolve bridge and FilmLab render, which an agent could not infer from the schema or annotations.

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?

The description is long but appropriate for a complex nested mutation tool; it front-loads the core write action, the alternative, and the atomicity guarantee. Some details repeat the very thorough schema, notably around clip_id and tempo, so it is effective but not maximally tight.

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 complex tool with nested objects, no output schema, and multiple modes, the description covers the write path, read-back path, validation behavior, concurrency error, identity semantics, and known downstream gaps. An agent has enough context to invoke it correctly and interpret major failure modes.

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 detailed per-parameter docs already carry most semantics. The description still adds useful cross-parameter meaning: sequence_id's dual write/read-back mode, clip_id's identity-preserving effect when reworking a cut, tempo vs tempo_kurve precedence, and the consequence of omitting clip_id (orphaned bindings).

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?

The description states a specific verb and resource: 'Write a WHOLE cut into a sequence in one call', covering ordered clips, dissolves, and an optional bed. It explicitly distinguishes this from lab_get_sequence and from chaining lab_add_clip calls, so an agent can select it without opening sibling schemas.

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?

It gives explicit alternatives: prefer this over a chain of lab_add_clip when the whole cut is already known, use lab_get_sequence to read, and pass sequence_id without a manifest to read back a stored cut before changing it. It also states that the Resolve bridge does not go through this tool, which prevents a plausible wrong selection.

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

All FilmLab toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources