Agnes AI MCP Server
The Agnes AI MCP Server provides free text-to-image and text-to-video generation via the Agnes AI API, with automatic local downloads to ~/agnes_output.
text_to_image: Generate 1β4 images from a text prompt using
agnes-image-2.0-flashoragnes-image-2.1-flashmodels, with optional reference images for composition and configurable output size.image_to_image: Transform existing images by providing one or more reference image URLs combined with a text prompt (batch up to 4 images).
text_to_video: Generate videos from a text prompt (and optionally images), with control over resolution (up to 1080p), frame count (up to ~18s), frame rate, inference steps, and seed.
image_to_video: Animate a static image into a video by providing an image URL or base64 Data URI and a prompt describing the desired motion.
keyframe_animation: Create a smooth video transition between 2 or more keyframe images, guided by a text prompt.
check_video_status: Poll the status of an asynchronous video generation task using a
video_idortask_id, retrieving progress, URL, and metadata.
All features are completely free ($0 per image, $0 per second of video) and compatible with Claude Desktop, Cursor, Windsurf, and any MCP stdio client.
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., "@Agnes AI MCP Servergenerate an image of a futuristic cityscape at night"
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.
ο»Ώ
π¨ Agnes AI MCP Server
Free Text-to-Image & Text-to-Video generation via Agnes AI
English | δΈζ
π Quick Start
# 1. Install (one command)
pip install agnes-mcp
# 2. Get a free API key at https://agnes-ai.com
# 3. Add to your MCP client config:Claude Desktop / Cursor / Windsurf (claude_desktop_config.json or equivalent):
{
"mcpServers": {
"agnes-mcp": {
"command": "uvx",
"args": ["agnes-mcp"],
"env": {
"AGNES_API_KEY": "your-api-key-here"
}
}
}
}Codex (config.toml):
[mcp_servers.agnes_mcp]
command = "uvx"
args = ["agnes-mcp"]
[mcp_servers.agnes_mcp.env]
AGNES_API_KEY = "your-api-key-here"That's it! Now you can generate images and videos directly from your AI assistant.
Related MCP server: TensorsLab MCP Server
β¨ Why Agnes MCP?
Feature | Agnes MCP | Other AI Image Services |
Price | $0 / image, $0 / second | $0.02 - $0.08 / image |
Text-to-Image | β 2 models (2.0 & 2.1 Flash) | β Usually 1 model |
Image-to-Image | β Reference image + prompt | β or limited |
Batch Generation | β 1-4 images at once | β |
Text-to-Video | β Up to 18s, 1080p | β or paid only |
Image-to-Video | β Static image β video | β or paid only |
Multi-image Video | β Keyframe animation | β |
Auto Download | β Saves locally automatically | β Manual download |
MCP Standard | β Full compliance | Varies |
Yes, it's completely free. Agnes AI currently offers all image and video generation at $0. Just register and get an API key.
πΌοΈ Demo
Text-to-Image (agnes-image-2.1-flash)
"A majestic dragon flying over a Chinese mountain landscape at sunset, cinematic lighting, epic fantasy art"
Text-to-Image (agnes-image-2.0-flash)
"A cozy Japanese ramen shop at night, warm lantern light, rain falling, anime style"
π¦ Tools
Tool | Description | Example |
| Generate image(s) from text |
|
| Generate from reference image(s) + text |
|
| Generate video from text/image(s) |
|
| Animate a static image into video |
|
| Smooth transition between keyframe images |
|
| Check async video task status |
|
βοΈ Environment Variables
Variable | Required | Default | Description |
| Yes | - | Your Agnes AI API key |
| No |
| API base URL |
| No |
| Default image model |
| No |
| Default image size |
π Get a Free API Key
Visit https://agnes-ai.com
Create an account (free)
Go to Console β API Keys β Create
Copy the key and paste into your config
β Supported Clients
Claude Desktop
Codex (OpenAI)
Cursor
Windsurf
Cherry Studio
Any MCP client with
stdiotransport
π Changelog
v0.3.0 (2026-06-28)
β¨ New tool:
image_to_videoβ animate a static image into videoβ¨ New tool:
keyframe_animationβ smooth transitions between multiple keyframe imagesβ¨
text_to_video: addedmodeandnum_inference_stepsparametersβ¨
create_video_task/generate_video: supportmode(e.g.ti2vid,keyframes) andnum_inference_stepsβ 28 tests passing
v0.2.0 (2026-06-27)
β¨ New tool:
image_to_imageβ generate from reference image(s) + promptβ¨
text_to_image: batch generation (n: 1-4) and multi-image composition (images)β¨
text_to_video: multi-image video / keyframe animation (images)π Unified multi-image download logic
β 19 tests passing
v0.1.1 (2026-06-26)
π Initial public release
text_to_image, text_to_video, check_video_status
Async httpx with retry mechanism
Auto-download to local filesystem
π€ Contributing
See CONTRIBUTING.md for guidelines.
π License
MIT
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/MSWEIMZ/agnes-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server