Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@makerai-mcp list the video generation modes"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Maker AI - AI Product Photo, Video & Ad Generator for Ecommerce
A Model Context Protocol server that exposes the canonical Maker AI knowledge surface — video generation workflows, pricing, FAQ, official links — to MCP-compatible AI clients such as Claude Desktop, Cursor, Windsurf, and Continue. Read-only, no API keys, no quota, ~50 ms cold start.
Official website: https://makerai.online
Maker AI is an AI-powered creative studio built for ecommerce brands that need product content at scale. Users upload a product photo or paste a Shopify or Amazon store URL, and the platform generates studio-quality product images, short-form video ads, and UGC-style clips from that single input. Rather than coordinating photographers, video editors, and content creators separately, teams can produce all three content formats in one workflow. The platform draws on more than sixteen video generation models — including Sora, Kling, and Veo — selecting the appropriate model automatically based on the task. The result is a faster creative loop that lets brands test more variations without proportionally increasing production effort.
Related MCP server: Producer AI MCP Server
Multi-format output from one upload — a single product photo or store URL produces studio photos, video ads, and UGC-style clips without separate workflows for each format.
16+ video model access — the platform routes generation tasks to the most suitable model automatically, covering Sora, Kling, Veo Fast, and others without requiring manual model selection.
1,000+ AI avatar library — UGC-style clips can feature realistic digital humans speaking in multiple languages including Spanish, French, German, Arabic, Russian, Korean, and Japanese, removing the need to hire or brief human creators.
Platform-optimized export — content is formatted with native aspect ratios and pacing for TikTok, Instagram Reels, YouTube Shorts, Amazon listings, and Shopify product pages.
Proven ad hook templates — a library of structured templates based on high-performing ad formats helps teams produce on-brand creative without starting from a blank slate.
Inspiration library — ready-made examples demonstrate what finished outputs look like across different product categories and platforms, useful for briefing or for direct adaptation.
An Amazon seller needs fresh product listing images and short video clips for a seasonal campaign but lacks an in-house studio; they paste the product URL and export platform-ready assets the same day.
A DTC brand running paid social wants to A/B test six ad hook variations for a new product launch without engaging an agency for each iteration.
An ecommerce team expanding into French and Spanish markets generates localized UGC-style videos with AI avatars speaking each language rather than coordinating separate creator shoots.
A Shopify store owner wants professional-looking background-swapped product photos to replace raw supplier images on their product pages.
A growth team wants to refresh ad creative weekly to counter fatigue without increasing the content production budget.
Maker AI targets ecommerce operators who produce product content regularly and feel the friction of traditional production. The primary users are DTC brand owners, Amazon sellers, and in-house ecommerce growth teams at product-focused companies. It suits teams that run paid social campaigns, manage multiple product SKUs, or sell across several international markets — situations where the volume and variety of required content outpaces what a small team can produce through conventional means. Freelancers and small agencies managing multiple ecommerce clients will also find the multi-format workflow useful for keeping per-client production costs contained.
list_video_modesReturn the canonical list of video-generation modes the site supports. (Maker AI)
Input: no parameters. Returns: text/markdown.
get_pricingReturn the canonical pricing entry point for Maker AI.
Input: no parameters. Returns: text/markdown.
get_official_linksReturn the canonical list of official links for Maker AI (website, support, docs when available).
Input: no parameters. Returns: text/markdown.
site://makerai/video-modes — Available video-generation modes (text-to-video, image-to-video, etc.).
site://makerai/pricing — Canonical pricing entry point.
site://makerai/faq — Short FAQ generated from public site metadata.
site://makerai/links — Canonical URLs to share with users.
tell_me_about_makeraiSummarize what the site is, who it's for, and how it works. — Maker AI
try_video_mode_makeraiPick a video-generation mode for a stated creative intent. — Maker AI
npx -y @smithery/cli install makerai-mcp --client claude(Replace claude with cursor, windsurf, or continue for those clients.)
git clone https://github.com/rocnubie/makerai-mcp.git
cd makerai-mcp
pnpm installThen add to your MCP client config (claude_desktop_config.json for Claude Desktop, mcp.json for Cursor / Windsurf / Continue):
{
"mcpServers": {
"makerai-mcp": {
"command": "node",
"args": [
"/absolute/path/to/makerai-mcp/src/index.mjs"
]
}
}
}npx @modelcontextprotocol/inspector node src/index.mjsWebsite: https://makerai.online
Pricing: https://makerai.online/pricing
Community: https://discord.gg/makerai
Support: support@makerai.online
pnpm install
pnpm start # run the server over stdioMIT
Return the canonical list of official links for Maker AI (website, support, docs when available).
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided; description carries full burden. It states 'canonical list' implying stable data, but does not disclose update frequency or idempotency. Adequate but minimal.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence, no filler. Front-loaded with purpose. Every word earns its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given zero parameters and no output schema, the description covers the purpose adequately. Could list examples of links but not required.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
No parameters, so no schema gaps. Baseline of 4 is appropriate as description adds nothing beyond schema (which is empty).
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description states a specific verb 'Return the canonical list' and resource 'official links for Maker AI', clearly distinguishing it from siblings list_video_modes and get_pricing.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool vs alternatives. While siblings are distinct, the description could mention when to consult this tool (e.g., for static references) but does not.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Return the canonical pricing entry point for Maker AI.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must disclose behavioral traits. It only states 'Return', implying read-only, but lacks details on authentication requirements, caching, or side effects.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence with no extraneous words, conveying the essential information efficiently.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has no parameters and no output schema, the description is minimal. It identifies the resource but does not describe the return format or any prerequisites, leaving gaps in completeness.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
No parameters exist, so schema coverage is 100%. The description adds no parameter details, which is acceptable, but the baseline of 3 applies as no extra value is provided.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses a specific verb ('Return') and identifies the resource ('canonical pricing entry point for Maker AI'). It clearly states what the tool does, though it does not differentiate from siblings beyond the resource name.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives. Sibling tools exist (list_video_modes, get_official_links) but no comparison or context is given.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Return the canonical list of video-generation modes the site supports. (Maker AI)
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, and the description lacks behavioral details such as whether the result is cached, if it's a read-only operation, or any side effects. It simply states 'Return' without elaborating on behavior.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, clear sentence with no unnecessary words. It effectively communicates the tool's purpose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The explanation is mostly sufficient for a simple tool with no parameters and no output schema, but it could mention the output format (e.g., a list of mode names) for completeness.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool has zero parameters and schema coverage is 100%, so the description does not need to add parameter information. The baseline for zero params is 4.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Return') and resource ('canonical list of video-generation modes'). It distinguishes from siblings like get_pricing and get_official_links.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when or when not to use this tool vs alternatives. For a simple list retrieval, usage is implied but not explicitly stated.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
v0.1.0get_official_linksget_pricinglist_video_modesScored across 3 tools
Each tool has a clearly distinct purpose: listing video modes, getting pricing, and retrieving official links. No overlap in functionality.
All tools follow the verb_noun pattern consistently using lowercase and underscores (list_video_modes, get_pricing, get_official_links).
With 3 tools, the server is well-scoped for providing key reference information about Maker AI. No superfluous or missing core tools.
The tool set covers the main informational needs: video modes, pricing, and official links. A minor gap might be a tool for detailed model specs, but the surface is largely complete for its apparent purpose.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Talk to your public-facing AI from any MCP client — Claude, ChatGPT, Cursor, Cline, Windsurf.
Knowledge base MCP for AI agents on iknow.dev. Search, read, and maintain via OAuth.
Your memory, everywhere AI goes. Build knowledge once, access it via MCP anywhere.
Read-only MCP server for Flamel.ai's public content: company overview, blog, case studies, FAQs.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/rocnubie/makerai-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
