PostNitro

Generate Video Post with AI

postnitro_generate_video

Generate a video post (postType VIDEO) using PostNitro's AI engine. Returns an embedPostId to track progress.

The content is AI-generated from your aiGeneration prompt — you do NOT provide slides. Each slide the AI writes becomes a scene in the video. (To supply your own scene content instead, use postnitro_import_video.)

Output: 'DESIGN' (default) creates the design without rendering; 'MP4' renders the video file and requires videoSettings (duration, optional audio track).

templateId, brandId, presetId, and responseType are optional if you've saved defaults via postnitro_set_defaults. Otherwise provide them here (use the list tools to find valid IDs).

Use postnitro_check_status to monitor, then postnitro_get_output to retrieve. Or use postnitro_generate_video_and_wait for one step.

Input Schema

TableJSON Schema

Name	Required	Description
`brandId`	No	Brand ID (optional if saved via postnitro_set_defaults)
`presetId`	No	AI preset ID (optional if saved via postnitro_set_defaults)
`templateId`	No	Template ID (optional if saved via postnitro_set_defaults)
`requestorId`	No	Optional custom tracking ID
`aiGeneration`	Yes
`responseType`	No	Output format for a video. 'DESIGN' (default) creates the design without rendering — fastest, and enough for scheduling or finishing in the editor. 'MP4' renders the video file and requires videoSettings. A video cannot be rendered as PDF or PNG.
`videoSettings`	No	Video render settings. REQUIRED when responseType is 'MP4' (a render needs a duration); optional for 'DESIGN'. When this video is later scheduled as a reel, the API reuses these settings automatically.
`generateImages`	No	Optional AI image generation — include this object to enable it, omit it for no images. When included, `context` is required and you (the agent) must author it from the post. Best-effort: the post still COMPLETES if images fail or aren't permitted (free plan / exhausted AI-image quota); check the GENERATE_IMAGES step via postnitro_check_status. Requires a paid plan, consumes the org's AI-image quota (separate from post credits), and adds latency.

Output Schema

TableJSON Schema

Name	Required	Description
`status`	Yes	Initial job status ('PENDING')
`message`	No	Message returned by the PostNitro API
`success`	Yes	True when the job was accepted
`nextStep`	Yes	The suggested follow-up call
`warnings`	No	Non-fatal issues worth surfacing to the user (e.g. AI image generation did not complete)
`embedPostId`	Yes	Generation-job ID — pass to postnitro_check_status, then postnitro_get_output
`usedDefaults`	Yes	The values actually applied — explicit arguments, saved defaults, or an auto-selected sole candidate

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

First observedSep 7, 2026

TDQS

A5/5.0

Behavior5/5

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

Discloses asynchronous behavior (returns embedPostId for progress tracking), best-effort image generation with failure/completion notes, quota and plan requirements, latency impact, and audio ID validation semantics (rejects URLs/non-audio IDs). It also explains rendering limitations (cannot be PDF/PNG) and future reuse of videoSettings for reels.

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 detailed but every sentence serves a purpose, covering core action, async workflow, parameter nuances, and cross-tool references. The structure uses clear paragraphs and inline parentheticals that keep related information together without redundancy.

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?

Given the output schema is present, the description still adds key operational context: that a returned embedPostId is used for tracking, how to check results and retrieve output, the distinction between DESIGN and MP4, and the conditions under which images may fail. This is sufficient for an agent to invoke the tool correctly.

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

Parameters5/5

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

Adds substantial meaning beyond the schema: explains that slides become scenes, clarifies videoDuration bounds and requirement, specifies audioId must be a media ID not URL, instructs the agent to author generateImages.context itself rather than asking the user, and details imageStrategy/imagePlacement behavior. This goes well beyond the raw property descriptions.

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 the tool generates a video post via AI and returns an embedPostId, clearly distinguishing it from import-based video creation by noting it uses AI-generated scenes rather than user-supplied slides. It also mentions the postType VIDEO and contrasts with postnitro_import_video.

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?

Provides explicit guidance on when to use which responseType, when videoSettings is required, and references related tools for defaults, listing, status checking, and retrieval. It also names the synchronous alternative postnitro_generate_video_and_wait, making usage conditions clear.

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

All PostNitro tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4/5.0

Disambiguation4/5

Most tools are clearly separated by verb and noun (generate_carousel vs generate_image vs generate_video, import_* vs generate_*). The generic convenience names like generate_and_wait and import_and_wait are slightly ambiguous, but their descriptions and the _wait/_schedule suffixes make them distinguishable.

Naming Consistency4/5

All tools share the postnitro_ prefix and snake_case verb-first convention. A few compound names (generate_and_schedule, import_and_wait) break the strict verb_noun pattern, but the convention is otherwise consistent and predictable.

Tool Count2/5

With 35 tools, the surface exceeds the rubric's 25+ 'too many' threshold. Many entries are convenience wrappers (_wait, _and_schedule) around the same core operations and could be consolidated to reduce overload.

Completeness4/5

The domain is well covered: generation, import, output retrieval, scheduling, brands, social accounts, audio, templates, presets, and defaults. Minor gaps remain (no delete_brand, no upload/connect for audio/social accounts), but those are largely external or non-critical.

Resources

Need Help?