io.github.wubin1836/ai-hive-aigc
AI Hive AIGC MCP server enables commercial image and video generation for e-commerce, marketing, and advertising, with model discovery, media upload, generation tasks, and polling.
README
AI Hive AIGC MCP Server
<!-- mcp-name: io.github.wubin1836/ai-hive-aigc -->
AI Hive AIGC is a Streamable HTTP MCP server for commercial image, video, e-commerce, marketing and advertising generation. One server exposes model discovery, media upload, image generation, video generation, e-commerce workflows, advertising/TVC workflows and task polling.
AI Hive AIGC MCP 为中文用户和全球开发者提供统一的图片与视频生成入口,覆盖 Nano Banana Pro、GPT Image 2、Seedream、Seedance、MiniMax H3、Wan、HappyHorse,以及电商主图、商品详情页、Listing、PDP、广告、TVC、带货、种草、短剧和漫剧场景。
MCP endpoint
https://ai-hive.iclip.cn/api/mcp
Transport: Streamable HTTP.
Authentication
The public endpoint advertises OAuth 2.1 protected-resource metadata and supports PKCE. The local reference server also supports an AI-HIVE API key in the request header:
x-ai-hive-api-key: sk-api-...
For local development, set AI_HIVE_API_KEY. The local server intentionally allows unauthenticated MCP discovery so registries can index the tool catalog; generation calls fail safely until a user provides a key.
Tools
ai_hive_list_modelsai_hive_upload_mediaai_hive_generate_imageai_hive_generate_ecommerce_imageai_hive_generate_videoai_hive_generate_ecommerce_videoai_hive_generate_advertising_videoai_hive_get_task
Generation tools are non-idempotent and can incur charges. After receiving a task_id, query that task instead of resubmitting the same request.
Run locally
npm install
npm test
npm start
Health check: GET /health
Static registry card: GET /.well-known/mcp/server-card.json
The production MCP is hosted by AI-HIVE and is not deployed from this repository. This repository provides the public protocol reference, tool implementation, tests, Registry metadata and policy documents.
Docker
docker build -t ai-hive-mcp .
docker run --rm -p 3000:3000 -e AI_HIVE_API_KEY=sk-api-example ai-hive-mcp
Smithery configuration schema
When publishing, use a session configuration field injected as an HTTP header:
{
"type": "object",
"properties": {
"apiKey": {
"type": "string",
"title": "AI Hive API Key",
"x-from": { "header": "x-ai-hive-api-key" }
}
},
"required": ["apiKey"]
}
License
MIT
Policies and support
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.