freedom-mcp

Generate video

generate_video

Destructive

Generate a video clip for the company (xAI Imagine Video 1.5, 3 credits): text-to-video, image-to-video, multi-image reference (up to 7), or video edit with native audio. Use when an operator or agent needs social, product, narrated, or brand video up to 15s / 1080p. This is the only video generation door.

Routing: Prefer generate_image_xai → user approves → generate_video(artifact_id) over pure text-to-video when an approved still exists; pure T2V is fine when none exists. MCP/autonomous: artifact_id, not image_url.

[sensitive-tier, initiates a multi-step agent process — first use may require a manager's approval; a from-now-on approval makes future calls seamless, a just-once approval re-asks next time. Call it on the first clear ask; the card is the yes — do not re-ask in chat.]

Input Schema

TableJSON Schema

Name	Required	Description
`prompt`	Yes	Detailed description of the video to generate. Include visual scene, audio/voice direction, mood, and brand elements. For multi-image: describe how the subjects from each image interact. For video editing: describe the changes to make. Avoid precise on-screen text animation (prefer burned-in design tools) and many incompatible camera cuts without clear staging — both are still hard for short-form video models.
`duration`	No	Video duration in seconds (1–15, primitive max). Use the length the shot needs — not an FO soft cap. Default 5 only when omitted. Not supported for video editing.
`companyId`	Yes	FreedomOS company id to act within (you must be a member). Required for company-scoped tools.
`image_url`	No	Chat door only. MCP/autonomous must pass artifact_id — a URL is refused and never queued as an Allow card.
`video_url`	No	Chat door only. MCP/autonomous must pass artifact_id of the video to edit (input capped at 8.7s).
`image_urls`	No	Chat door only (up to 7). MCP/autonomous: artifact_ids.
`resolution`	No	Video resolution. 480p (fast draft, API default when omitted), 720p (HD), 1080p (full HD on text-to-video and image-to-video) — prefer the highest resolution that fits the deliverable, not a permanent draft default. Reference-to-video is automatically clamped to 720p (primitive). Not supported for video editing.
`artifact_id`	No	ID of a single existing artifact from the MEDIA IN THIS CONVERSATION block. The system resolves a fresh signed URL and auto-detects: image artifacts → image-to-video, video artifacts → video editing. For multiple images, use artifact_ids instead.
`artifact_ids`	No	Array of artifact IDs (up to 7, primitive max) for reference-to-video. System resolves fresh signed URLs for each.
`aspect_ratio`	No	Aspect ratio. Default: 16:9 (YouTube/hero/landscape); 9:16 (Reels/Shorts/Stories); 1:1 (feed square). For image-to-video, defaults to the input image ratio. Not supported for video editing.
`save_to_drive`	No	If true, also save the video to Google Drive. Defaults to false.

Schema Changelog

Changes observed during successful MCP inspections.

Changed6 schema fields changedSep 23, 2026

changedInput schema / properties / aspect_ratio / description

Previous value: -"Aspect ratio. Default: 16:9. For image-to-video, defaults to the input image ratio. Not supported for video editing."New value: +"Aspect ratio. Default: 16:9 (YouTube/hero/landscape); 9:16 (Reels/Shorts/Stories); 1:1 (feed square). For image-to-video, defaults to the input image ratio. Not supported for video editing."

changedInput schema / properties / image_url / description

Previous value: -"URL of a single still image to animate (image-to-video mode). Use image_url from a previous generate_image result. For multiple images, use image_urls instead."New value: +"Chat door only. MCP/autonomous must pass artifact_id — a URL is refused and never queued as an Allow card."

changedInput schema / properties / image_urls / description

Previous value: -"Array of image URLs (up to 7, primitive max) for reference-to-video. Combine mascot, person, product, brand assets. Use signed URLs from MEDIA IN THIS CONVERSATION. For a single image, use image_url instead."New value: +"Chat door only (up to 7). MCP/autonomous: artifact_ids."

changedInput schema / properties / prompt / description

Previous value: -"Detailed description of the video to generate. Include visual scene, audio/voice direction, mood, and brand elements. For multi-image: describe how the subjects from each image interact. For video editing: describe the changes to make."New value: +"Detailed description of the video to generate. Include visual scene, audio/voice direction, mood, and brand elements. For multi-image: describe how the subjects from each image interact. For video editing: describe the changes to make. Avoid precise on-screen text animation (prefer burned-in design tools) and many incompatible camera cuts without clear staging — both are still hard for short-form video models."

changedInput schema / properties / resolution / description

Previous value: -"Video resolution. 480p (fast draft), 720p (HD), 1080p (full HD on text-to-video and image-to-video). Reference-to-video is automatically clamped to 720p (primitive). Not supported for video editing."New value: +"Video resolution. 480p (fast draft, API default when omitted), 720p (HD), 1080p (full HD on text-to-video and image-to-video) — prefer the highest resolution that fits the deliverable, not a permanent draft default. Reference-to-video is automatically clamped to 720p (primitive). Not supported for video editing."

changedInput schema / properties / video_url / description

Previous value: -"URL of an existing video to edit (video editing mode). Describe the edits in the prompt. Input capped at 8.7 seconds (primitive)."New value: +"Chat door only. MCP/autonomous must pass artifact_id of the video to edit (input capped at 8.7s)."

Changed6 schema fields changedAug 7, 2026

changedInput schema / properties / artifact_ids / description

Previous value: -"Array of artifact IDs (up to 7) from the MEDIA IN THIS CONVERSATION block for multi-image video generation. The system resolves fresh signed URLs for each. Example: pass the mascot image artifact + founder photo artifact to create a video where they interact."New value: +"Array of artifact IDs (up to 7, primitive max) for reference-to-video. System resolves fresh signed URLs for each."

changedInput schema / properties / duration / description

Previous value: -"Video duration in seconds (1-15). Default: 5. Not supported for video editing."New value: +"Video duration in seconds (1–15, primitive max). Use the length the shot needs — not an FO soft cap. Default 5 only when omitted. Not supported for video editing."

changedInput schema / properties / image_urls / description

Previous value: -"Array of image URLs (up to 7) for multi-image video generation. Combine a mascot, a person, product shots, and brand assets into one cohesive video. Use signed URLs from the MEDIA IN THIS CONVERSATION block. For a single image, use image_url instead."New value: +"Array of image URLs (up to 7, primitive max) for reference-to-video. Combine mascot, person, product, brand assets. Use signed URLs from MEDIA IN THIS CONVERSATION. For a single image, use image_url instead."

changedInput schema / properties / resolution / description

Previous value: -"Video resolution. 480p (default, faster) or 720p (HD). Not supported for video editing."New value: +"Video resolution. 480p (fast draft), 720p (HD), 1080p (full HD on text-to-video and image-to-video). Reference-to-video is automatically clamped to 720p (primitive). Not supported for video editing."

changedInput schema / properties / resolution / enum

Previous value: -[
-  "480p",
-  "720p"
-]New value: +[
+  "480p",
+  "720p",
+  "1080p"
+]

changedInput schema / properties / video_url / description

Previous value: -"URL of an existing video to edit (video editing mode). Describe the edits in the prompt. Input capped at 8.7 seconds."New value: +"URL of an existing video to edit (video editing mode). Describe the edits in the prompt. Input capped at 8.7 seconds (primitive)."

First observedJul 19, 2026

TDQS

A4.5/5.0

Behavior5/5

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

The description adds substantial behavior beyond the annotations: it discloses sensitivity tier, multi-step agent process, manager approval semantics, credit cost, the 'card is the yes' confirmation model, and the instruction not to re-ask in chat. The destructiveHint=true annotation is consistent with the described side-effecting, approval-gated workflow; there is no contradiction.

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 front-loaded with the core purpose, then routing, then approval behavior; every sentence adds operational value. It is longer than minimal, but the density is justified for a side-effecting, approval-gated video tool with many mode distinctions.

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

Completeness4/5

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

For a complex 11-parameter tool with no output schema, the description covers purpose, scope, routing, approval, and credit cost well. The main gap is that it does not explicitly describe what the final output/returned result looks like after the approval card is resolved, though the card flow partially addresses this.

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?

Schema description coverage is 100%, and the schema already provides detailed parameter guidance for every field, including artifact_id vs artifact_ids, resolution clamping, duration limits, and aspect-ratio defaults. The tool description mostly reinforces the MCP/autonomous artifact_id rule rather than adding new parameter meaning beyond the schema, so the baseline of 3 is appropriate.

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 opens with a specific verb+resource: 'Generate a video clip for the company' and enumerates the exact modes: text-to-video, image-to-video, multi-image reference, and video edit. It also states 'This is the only video generation door,' which differentiates it from image-generation siblings like generate_image_xai and generate_carousel.

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 when-to-use guidance: 'Use when an operator or agent needs social, product, narrated, or brand video up to 15s / 1080p.' It names the alternative workflow: 'Prefer generate_image_xai → user approves → generate_video(artifact_id) over pure text-to-video when an approved still exists.' It also gives an explicit MCP/autonomous routing rule about artifact_id versus image_url.

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

All freedom-mcp tools Inspect

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

Need Help?