Retiplex
Server Details
Retiplex is #1 tool for agents that handles the whole video ad production process. Tailored to custom offer. From ad strategy to ready-to-post video with just a few tool calls.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 24 tools
Most tools occupy clearly distinct slots in a linear pipeline (media upload, cast, moments, brief, script, storyboard, video), and the descriptions explicitly disambiguate close pairs like set_actor vs set_narrator_voice and set_product vs update_product_media. The one murky cluster is get_project / show_project / project_card, where 'project_card reads its own data' is opaque and overlaps with the other two read tools, plus create_project vs set_product overlap in inputs.
Nearly all tools follow a verb_noun snake_case pattern grouped by verb family (add_*, remove_*, set_*, get_*, generate_*, list_*), which makes the pipeline readable. The single deviation is the noun-only 'project_card' (and arguably 'view_images' vs 'show_project'), but the convention is otherwise stable.
24 tools is at the heavy end for what is essentially one workflow, and several could be consolidated (project_card into get_project, get_video_status into get_project, view_images into get_project). Each tool does map to a real pipeline step, so it isn't bloated for bloat's sake, but the surface is borderline large.
The lifecycle is well covered end-to-end: account checks, project creation/listing, media upload with finalize, cast and moment management, brief/actor/voice setup, script and storyboard generation, video start/status/resume, and viewing. Gaps are modest: no delete/archive project, no cancel of an in-flight video generation, and no scene-level editing after a storyboard is generated.
Publisher details
- Operator
- Retiplex · Publisher source
- Operator website
- https://www.retiplex.com · Publisher source
- Vendor relationship
- First-party
- Documentation
- https://app.retiplex.com/help/agents · Publisher source
- Privacy policy
- Not provided
- Trust center
- Not available
- Restrictions
- Sign up required, OAuth authentication.
Available Tools
24 toolsadd_momentAdd required momentAInspect
Optional — except for uploaded videos. Adds a required moment: a scene the ad must contain; the script is written around it and the storyboard places it where it fits. Without moments the script and storyboard decide everything, which is fine. BUT an uploaded video only appears in the ad through a custom-footage moment — uploading it alone does nothing; give footage (its media_id and the range to play, muted). Types: product-shot (the product in frame, held or used by whoever you tag — their face shows), product-shot-faceless (the same, but the narrator shows only their hands — no face), b-roll (supporting footage: a place, object, mood), product-action (the product in motion, from its photos), talking-person (the narrator says dialogue to camera), custom-footage. Tag who's in frame in the description with @[Name] from get_project's cast (e.g. "@[Main Character] pours @[Glow Serum] into her palm"). Add moments before generate_script; the total must fit the script's length.
Inputs: type (required), project_id (required), description (required), footage, +2 more.
add_subjectAdd subjectAInspect
Optional. Adds someone or something to the cast beyond the narrator and the product — a side character (kind person), a pet, or an object — so moments can feature them by tagging @[Name]. Skip it unless the ad needs them. The image is either yours (image_url, or upload_id from create_media_upload; a photo meeting the requirements, ≥480×480 px) or generated (generate: true, a few credits, ready in about a minute: a person is drawn from archetype, the actor form's fields; a pet or object from description). Add subjects before the moments that tag them, and both before generate_script.
Inputs: kind (required), name (required), project_id (required), description (required), +4 more.
create_media_uploadCreate media uploadAInspect
For a photo or video file on the user's machine (needs an agent that can run curl or make HTTP requests). Returns a one-time upload_url: PUT the file's bytes there with its Content-Type header (the returned curl does exactly that), then call finalize_media_upload. Media requirements:
Photos: JPEG, PNG or WebP; at least 480×480 px; at most 15 MB. Clear, well-lit shots of the real product, one product per photo, no collages or heavy text overlays.
Videos: MP4 or MOV (H.264 recommended); 1–60 seconds; at most 50 MB; vertical 9:16 recommended. Clips play muted. A video only appears in the ad through a custom-footage moment (add_moment, type custom-footage): uploading it alone does nothing.
Physical products: tag every photo with the view it shows (front, left, rear, a 3/4 view…,
detailfor a close-up,size-referencefor a scale shot). A front photo is strongly recommended.detailphotos, and every photo of a digital product or service, need a description (≤240 characters) of what they show.At most 8 files per call.
Inputs: project_id (required), content_type (required).
create_projectCreate projectAInspect
Starts a new video ad for a product. Give product_url to import it, or product_name and product_description; add photos and videos by URL with media. Returns the project and the next step.
Inputs: name, media, language, product_url, +5 more.
finalize_media_uploadFinalize media uploadADestructiveInspect
Checks a file PUT to an upload_url against the requirements and adds it to the project's media. If file inspection, classification, or saving fails, the uploaded file is deleted from Retiplex storage and the error is returned. A deleted upload must be uploaded again before retrying.
Inputs: upload_id (required), project_id (required), angle, description.
generate_scriptGenerate scriptADestructiveInspect
Writes the voiceover script from the brief (calling it again writes a different variation), or saves script if you pass one. target_seconds sets the length (10–120s; trial accounts less). Changing the script after a storyboard means regenerating the storyboard.
Inputs: project_id (required), script, target_seconds.
generate_storyboardGenerate storyboardADestructiveInspect
Plans the scenes from the script, actor and product photos. Runs in the background for 1–3 minutes: poll get_project until storyboard.scenes > 0, then review the scenes with the user. Needs a paid plan. Regenerating replaces the scenes. video_quality picks the models the video is filmed with: "standard" (default — Grok Imagine and MiniMax H3, affordable) or "premium" (Seedance 2.5 for every scene, most realistic, about 29 credits per second of video; English only for now). Ask the user which they want before the first storyboard.
Inputs: project_id (required), video_quality.
get_accountGet accountARead-onlyInspect
The signed-in user's Retiplex account: credit balance, plan, whether it can generate videos, and the longest script it allows. Call this first, and before anything that spends credits.
Inputs: no named parameters.
get_projectGet projectARead-onlyInspect
A project's state: product and its media (each with what it still needs), the cast (the @[Name] tags scenes can use), moments, brief, actor (previewUrl: their portrait), script, storyboard (with its scenes once generated) and the current step, plus nextTool to call. Poll this while a storyboard or a subject image generates. To see the photos and the portrait, call view_images.
Inputs: project_id (required).
get_video_statusGet video statusARead-onlyInspect
Progress of a project's video generation, and the finished video's URL once it's rendered. Poll every couple of minutes, not faster.
Inputs: project_id (required).
list_formatsList ad formatsARead-onlyInspect
The ad formats (narrative templates) a project can use, for set_creative_brief. custom has no fixed structure: describe the ad as an idea instead.
Inputs: no named parameters.
list_projectsList projectsARead-onlyInspect
The user's 20 most recent video projects.
Inputs: no named parameters.
project_cardProject cardCRead-onlyInspect
The project card's data, read by the card itself.
Inputs: project_id (required).
remove_momentRemove momentBDestructiveInspect
Removes a required moment (from get_project's moments) from the ad.
Inputs: moment_id (required), project_id (required).
remove_subjectRemove subjectADestructiveInspect
Removes a subject (or a pending/failed subject image) that no moment tags.
Inputs: project_id (required), subject_id (required).
resume_video_generationResume video generationAInspect
Retries a failed or stalled video generation from where it stopped, when get_video_status suggests it.
Inputs: project_id (required).
set_actorSet actorADestructiveInspect
Casts the on-camera narrator and renders their portrait, which every scene is generated from — the app's actor form. Leave archetype out to cast someone fitting the audience automatically. Pass archetype to design them: for a project with an actor, only the fields you give change (e.g. just clothing); a first actor needs every field except facialFeatures. Also sets the narrator's spoken language and accent (language, language_accent) when given; to change only those, use set_narrator_voice, which doesn't recast. Each call renders a new portrait (7 credits, 10 on Premium). Show the user previewUrl: it is the actor Retiplex uses; never generate or substitute a picture of them yourself.
Inputs: project_id (required), language, archetype, language_accent.
set_creative_briefSet creative briefADestructiveInspect
Sets the ad's format and campaign facts (who it's for, the benefit to sell, the action to drive). Facts you leave out are deduced from the product (a few credits). For the custom format pass idea — the ad you have in mind, in your own words — and a full brief is written from it.
Inputs: project_id (required), idea, format, funnel_stage, +3 more.
set_narrator_voiceSet narrator voiceADestructiveInspect
Sets the narrator's spoken language and accent (the app's "Narrator's voice") without touching the actor. Free. The script, every talking scene, the voice and the captions follow it. A script written in the old language must be regenerated (generate_script) or rewritten and passed as script; get_project says so in scriptWarning. An existing storyboard goes stale.
Inputs: project_id (required), language, language_accent.
set_productSet productCDestructiveInspect
Changes a project's product, or adds photos and videos to it. Same inputs as create_project.
Inputs: project_id (required), media, product_url, product_name, +2 more.
show_projectShow projectARead-onlyInspect
Shows the user a live card of the project: its progress, the actor's portrait, the product photos, the storyboard's scenes and, once rendered, the video to watch. It updates itself while a storyboard or video generates. Use it whenever the user wants to see the project or the result; in clients that can't display it, share the URLs from get_project instead.
Inputs: project_id (required).
start_video_generationStart video generationAInspect
Generates the video from the storyboard: hook, voice, every scene, then the final render. Takes 10–30 minutes and spends the estimate get_project returns (estimatedVideoCredits). Confirm that with the user and pass it as max_credits. Poll get_video_status.
Inputs: project_id (required), max_credits (required).
update_product_mediaUpdate product mediaADestructiveInspect
Classifies a product photo or video (its view angle, its description) or removes it. Look at each photo get_project lists with needs (view_images shows them, captioned with their media_id), and tag it with what you see. Media requirements:
Photos: JPEG, PNG or WebP; at least 480×480 px; at most 15 MB. Clear, well-lit shots of the real product, one product per photo, no collages or heavy text overlays.
Videos: MP4 or MOV (H.264 recommended); 1–60 seconds; at most 50 MB; vertical 9:16 recommended. Clips play muted. A video only appears in the ad through a custom-footage moment (add_moment, type custom-footage): uploading it alone does nothing.
Physical products: tag every photo with the view it shows (front, left, rear, a 3/4 view…,
detailfor a close-up,size-referencefor a scale shot). A front photo is strongly recommended.detailphotos, and every photo of a digital product or service, need a description (≤240 characters) of what they show.At most 8 files per call.
Inputs: media_id (required), project_id (required), angle, remove, +1 more.
view_imagesView imagesARead-onlyInspect
Shows you the project's images so you can look at them: by default the actor's portrait and every product photo that still needs classifying (all photos once none do), each captioned with its media_id. Use it before update_product_media to see which view each photo shows. These are the images Retiplex uses; show the user their URLs, never an image of your own.
Inputs: project_id (required), actor, media_ids.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
AI video studio for agents — script to MP4, b-roll sourcing, Gemini QA. 43 tools.
AI image, video and audio generation for agents: banners, reveal videos, avatars, voice cloning.
AI video editor for agents: cut footage, add captions and motion graphics, export editable edits.
Make and edit real estate listing videos, photos and websites from your AI assistant.
Related MCP Servers
AlicenseAqualityBmaintenanceAI marketing agent and AI ad generator, 1,088 tools. Works as a Google Ads MCP, Meta Ads MCP, LinkedIn MCP, TikTok MCP, Instagram MCP and YouTube MCP in one server. Research competitors' winning ads, make on-brand image and video ads with your real product, publish and schedule to your own accounts, and run paid ads (new campaigns start paused). Free to start, no markup on models.22144,717 npm7MIT
inReels MCPofficial
AlicenseNot gradedqualityCmaintenanceEnables AI agents to generate video ads, UGC ads, static image ads, voiceovers, and faceless videos, with tools for quoting, model discovery, asset upload, and run status checks.MIT- AlicenseNot gradedqualityDmaintenanceReplicate viral TikTok slideshows in your niche by talking to your agent. It generates images locally or via API and assembles the final result.1MIT
- AlicenseNot gradedqualityBmaintenanceEnables AI agents to create and edit vertical 9:16 video ads from a brand’s own footage, a reference ad, or an idea, with storyboard validation, captions, voice-over, sound design, deterministic ffmpeg rendering, and visual quality control.56 PyPI1MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.