A
licenseNot graded
qualityA
maintenanceEnables AI clients to create, edit, validate, preview, and render Shotcut projects (saved as MLT XML) without operating the GUI, using structured timeline editing tools and local safety mechanisms.
4
MIT
Video Brief Manifest MCP Server
Video Brief Manifest MCP Server
A small local Model Context Protocol server that checks whether an AI video brief contains the structural signals needed for a useful human review before generation begins.
The server is intentionally model-agnostic. It does not call a video-generation API, send prompts to a hosted service, or claim a direct integration with any video model.
Why validate a brief first?
Video prompts often fail because the brief leaves one dimension implicit. The subject may be clear while the motion is vague, or the visual style may be detailed while the camera and audio direction are missing. Those gaps are much cheaper to find before a generation run.
This server checks five practical dimensions:
subject
motion
camera treatment
visual details
audio direction
It also flags two common contradictions: asking for both silence and an explicit sound cue, or combining a static camera with camera movement.
Related MCP server: @cocrates/video-edit-mcp
Tools
validate_video_brief
Accepts a draft brief and returns detected fields, missing fields, warnings, and clarifying questions.
build_video_brief_manifest
Builds a portable JSON manifest containing the brief, optional duration and aspect-ratio constraints, validation results, and the next recommended step.
Install and run
Requires Node.js 18 or newer.
npm install
npm startExample MCP client configuration:
{
"mcpServers": {
"video-brief-manifest": {
"command": "node",
"args": ["/absolute/path/to/video-brief-manifest-mcp/index.js"]
}
}
}Run the protocol-level smoke test:
npm testExample brief
A ceramic robot turns toward camera in a slow tracking shot, with cool rim lighting and quiet ambient room tone.
The validator detects all five structural dimensions and returns a clean report. A shorter brief such as "A robot in a room" produces questions for motion, camera, visual details, and audio direction.
Where structured prompt workflows fit
This pattern works independently of any generation backend. It is useful when a workflow expects one brief to coordinate subject, motion, camera treatment, visual details, and audio direction. Muse Video is one example of a prompt-led workflow organized around those dimensions. Its underlying model is presented on the current site as preview-stage, so this repository treats it only as a workflow example and makes no claim about public access, pricing, limits, performance, or direct integration.
Limitations
The validator checks structure, not creative quality. A complete brief may still be ineffective, and simple keyword rules may miss unusual phrasing. The output should be treated as a preflight checklist for human review, never as a promise that a generation model will produce a particular result.
License
MIT
Available Tools
2 toolsbuild_video_brief_manifestBuild Video Brief ManifestC
Return a portable JSON manifest containing the brief, optional delivery constraints, and validation results.
ParametersJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| brief | Yes | ||
| title | No | ||
| aspect_ratio | No | ||
| duration_seconds | No |
TDQS
C2.7/5.0
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of behavioral disclosure. It mentions the output contents but does not explain how validation is performed, whether the tool can fail (and how errors are surfaced), or any side effects. The term 'validation results' is ambiguous—does it validate the brief itself or aggregated validation data?
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 a single, concise sentence that front-loads the primary purpose. It is not bloated or redundant. However, it is so brief that it sacrifices substantive content, which is a slight penalty given the tool's complexity.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has four parameters, a validation focus, no output schema, and no annotations, the description is far too sparse. It does not explain the manifest structure, validation criteria, or how to handle validation failures. The sibling tool validate_video_brief is not referenced, leaving the integration unclear.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, so the description must compensate for the lack of parameter documentation. It categorizes parameters into 'brief' and 'optional delivery constraints,' which groups title, aspect_ratio, and duration_seconds conceptually, but does not explain their individual purposes, formats, or how they affect the manifest. This is insufficient for a tool with four parameters.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool returns a portable JSON manifest containing the brief, optional delivery constraints, and validation results. It identifies the verb ('return') and the resource (JSON manifest), and implies a distinction from validate_video_brief by including validation results. However, it could be more explicit about the tool's role in building vs. validating.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus the sibling validate_video_brief. There is no mention of appropriate contexts, prerequisites, or exclusions. The tool's relationship to validation is only implicit through the phrase 'validation results,' which does not offer actionable usage direction.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
validate_video_briefValidate Video BriefA
Check a draft video brief for subject, motion, camera, visual-detail, and audio-direction signals.
ParametersJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| brief | Yes | The draft video brief to validate. |
TDQS
A3.7/5.0
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the transparency burden. It discloses that the tool checks for specific signal types, which gives some behavioral insight. However, it does not describe what happens on validation failure, whether the tool is read-only, or what the return format is, leaving room for ambiguity.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, front-loaded sentence that states the action and the specific signal categories without any extraneous information. Every word contributes to understanding the tool's purpose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a tool with one parameter and no output schema, the description provides the core purpose and signals checked, but it lacks information about expected output, failure behavior, and usage context. The absence of these details makes it minimally complete but not fully contextual.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema documents the only parameter 'brief' with a description, achieving 100% coverage. The tool description does not add any additional semantic detail about the parameter, so the baseline score of 3 applies.
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 uses a specific verb ('Check') and resource ('draft video brief') and enumerates the exact signal categories (subject, motion, camera, visual-detail, audio-direction), making its function clear. This distinguishes it from the sibling tool 'build_video_brief_manifest', which likely creates a manifest rather than validating.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage when a draft video brief exists and needs validation, but it does not explicitly state when to use this tool versus the sibling 'build_video_brief_manifest'. No exclusions or alternative conditions are provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
2 tool updates
v1.0.0- First observed
build_video_brief_manifest - First observed
validate_video_brief
TDQS
A3.5/5.0
Scored across 2 tools
Disambiguation5/5
The two tools have clearly distinct purposes: one validates a video brief, the other builds a manifest from it. There is no overlap in their functions, so an agent can easily select the right tool.
Naming Consistency5/5
Both tools follow a consistent verb_noun pattern: validate_video_brief and build_video_brief_manifest. The naming is predictable and reflects the action performed.
Tool Count4/5
With only two tools, the server is on the low end of the typical range, but both tools are essential and complement each other for the server's narrow purpose. The count feels slightly thin but is appropriate for the specific task of validating and building a manifest.
Completeness5/5
The server covers the full workflow from validating a draft brief to generating the portable manifest. There are no obvious gaps in the stated purpose, as the two tools together provide a complete pipeline.
Maintenance
ActivitySlowing
ResponsivenessNo issues
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Connectors
Preflight QA for AI-agent deliverables with structured verdicts and repair guidance.
AI film lab for filmmakers: generate and review images/clips with input provenance, cost preflight
Deterministic preflight checks for credentials, fund transfers, writes, and prompt overrides.
Deterministic validation for AI-generated artifacts: JSON Schema, OpenAPI response, SQL syntax.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceEnables video editing via YAML/JSON edit specs, with validation and rendering using Remotion.13Apache 2.0
- FlicenseNot gradedqualityBmaintenanceEnables AI agents to validate and render branded videos from structured Video Specifications via the Model Context Protocol. Provides tools for health checks, video validation, and deterministic Remotion rendering.-
- AlicenseAqualityCmaintenanceEnables validating and verifying verifiable claims through structural checks, hash anchoring, and optional script execution, exposing self-test, validate, and verify tools over stdio.3MIT