Agnes Image MCP Server
Click on "Deploy 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., "@Agnes Image MCP Server Generate a photo of a golden retriever playing in the snow"
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.
Agnes Image MCP Server
MCP server for Agnes Image 2.1 Flash (text-to-image generation), connected via OpenAI-compatible API.
Features
Generate images from text prompts
Supports aspect ratios (1:1, 16:9, 9:16, 4:3, 3:4, etc.)
Custom resolution (1K~4K)
Multi-image generation
Returns clickable image URLs
Related MCP server: Gemini Flash Image MCP Server
Requirements
Node.js >= 18
A platform.agnes-ai.com API key
Install
cd agnes-image-mcp-server
npm install
npm startEnvironment Variables
Variable | Required | Default | Description |
| ✅ | — | Your Agnes AI API key |
|
| Model name | |
|
| API base URL |
CC-Switch / Claude Code Config
{
"mcpServers": {
"agnes-image": {
"type": "stdio",
"command": "npx",
"args": ["-y", "@kira4094/agnes-image-mcp-server"],
"env": {
"AGNES_API_KEY": "your-agnes-api-key"
}
}
}
}Tool: agnes_image_generate
Parameter | Type | Required | Description |
| string | ✅ | Text description (Chinese/English) |
| string | Resolution ( | |
| string | Aspect ratio ( | |
| number | Number of images (default 1) |
License
MIT
Available Tools
1 toolagnes_image_generateB
Generate an image using Agnes Image 2.1 Flash (text-to-image model). Supports OpenAI-compatible API at https://apihub.agnes-ai.com/v1. Excels at: creative illustration, concept art, UI mockups, photorealistic renders, Chinese-style art.
Inputs: prompt (required), n, size, ratio.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 1 tool
Only one tool exists, so there is no possibility of confusion or overlap. The tool's purpose is unmistakable.
The single tool name 'agnes_image_generate' is clear and follows a consistent object-verb structure, though the typical verb-noun order is reversed. Since there is only one tool, the pattern is internally consistent.
With exactly one tool, the server is minimal but appropriately scoped for a dedicated image generation service. It feels thin but not unreasonable for such a focused purpose.
The server's stated purpose is text-to-image generation, and the single tool fully covers that operation. There are no obvious gaps within the narrow domain, as additional features like editing or listing would be outside the stated scope.
Maintenance
Related MCP Connectors
AI image + video generation for agents: --flag prompt DSL, async generate/poll, x402 pay-per-use.
Uncensored image, image-to-video and chat generation for adult apps. OpenAI-compatible, pay per use.
LLM chat, text tools, image generation, editing, batch image jobs, and asynchronous video generation
Create images & video from any MCP agent — 17 models, spend limits, one URL.
Related MCP Servers
- -licenseAqualityNot gradedmaintenanceEnables generating and editing images using OpenRouter's API with Gemini 2.5 Flash Image model. Supports custom aspect ratios, iterative editing, and reference images for style transfer.6137 npm-
- AlicenseAqualityDmaintenanceEnables text-to-image generation, image editing, and multi-image composition using Google's Gemini 2.5 Flash Image API. Supports flexible aspect ratios and character consistency across generations.1MIT
- AlicenseAqualityCmaintenanceEnables text-to-image and text-to-video generation via the Agnes AI API, with support for multiple models, async video generation, and automatic file downloads.61MIT
- FlicenseAqualityCmaintenanceEnables AI assistants to generate images and videos via the Agnes AI API, supporting text-to-image, image-to-image, and video generation.31-