HuggingFace Spaces
About
MCP server that seamlessly integrates Hugging Face Spaces with AI assistants, enabling easy access to diverse AI models and tools without manual configuration.
Details
- Repository
- evalstate/mcp-hfspace
- License
- MIT
Explore
- Connects to any Hugging Face Space automatically
- Default space: black-forest-labs/FLUX.1-schnell for image generation
- Supports file upload, download, and URL inputs
- Private spaces supported with Hugging Face token
- Multiple server instances for different tokens/working directories
- Claude Desktop Mode with embedded image returns
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
HuggingFace SpacesCommand (node, npx, python, etc.)npxArguments-
Argument 1
-y -
Argument 2
@llmindset/mcp-hfspace -
Argument 3
--work-dir=~/mcp-files/ or x:/temp/mcp-files/ -
Argument 4
--HF_TOKEN=HF_{optional token} -
Argument 5
Qwen/Qwen2-72B-Instruct -
Argument 6
black-forest-labs/FLUX.1-schnell -
Argument 7
space/example/specific-endpint
Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
-
Argument 1
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
NPM Package is @llmindset/mcp-hfspace.
Install a recent version of NodeJS for your platform, then add the following to the mcpServers section of your claude_desktop_config.json file:
"mcp-hfspace": {
"command": "npx",
"args": [
"-y",
"@llmindset/mcp-hfspace"
]
}
Please make sure you are using Claude Desktop 0.78 or greater.
This will get you started with an Image Generator.
Supply a list of HuggingFace spaces in the arguments. mcp-hfspace will find the most appropriate endpoint and automatically configure it for usage. An example claude_desktop_config.json is supplied below.
By default the current working directory is used for file upload/download. On Windows this is a read/write folder at \users\<username>\AppData\Roaming\Claude\<version.number\, and on MacOS it is the is the read-only root: /.
It is recommended to override this and set a Working Directory for handling the upload and download of images and other file-based content. Specify either the --work-dir=/your_directory argument or MCP_HF_WORK_DIR environment variable.
An example configuration for using a modern image generator, vision model and text to speech, with a working directory set is below:
"mcp-hfspace": {
"command": "npx",
"args": [
"-y",
"@llmindset/mcp-hfspace",
"--work-dir=/Users/evalstate/mcp-store",
"shuttleai/shuttle-jaguar",
"styletts2/styletts2",
"Qwen/QVQ-72B-preview"
]
}
To use private spaces, supply your Hugging Face Token with either the --hf-token=hf_... argument or HF_TOKEN environment variable.
It's possible to run multiple server instances to use different working directories and tokens if needed.
available-files
A list of available file and resources. If the User requests things like 'most recent image' or 'the audio' use this tool to identify the intended resource.This tool returns 'resource uri', 'name', 'size', 'last modified' and 'mime type' in a markdown table
search-spaces
Use semantic search to find an endpoint on the `Hugging Face Spaces` service. The search term will usually be 3-7 words describing a task or activity the Person is trying to accomplish. The results are returned in a markdown table. Present all results to the Person. Await specific guidance from the Person before making further Tool calls.
FLUX_1-schnell-infer
Call the FLUX.1-schnell endpoint /infer
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"huggingface spaces": {
"cwd": "optional",
"env": {},
"args": [
"-y",
"@llmindset/mcp-hfspace",
"--work-dir=~/mcp-files/ or x:/temp/mcp-files/",
"--HF_TOKEN=HF_{optional token}",
"Qwen/Qwen2-72B-Instruct",
"black-forest-labs/FLUX.1-schnell",
"space/example/specific-endpint"
],
"command": "npx"
}
}
}Linux
{
"env": [],
"args": [
"-y",
"@llmindset/mcp-hfspace",
"--work-dir=~/mcp-files/ or x:/temp/mcp-files/",
"--HF_TOKEN=HF_{optional token}",
"Qwen/Qwen2-72B-Instruct",
"black-forest-labs/FLUX.1-schnell",
"space/example/specific-endpint"
],
"command": "npx"
}Macos
{
"cwd": "optional",
"env": [],
"args": [
"-y",
"@llmindset/mcp-hfspace",
"--work-dir=~/mcp-files/ or x:/temp/mcp-files/",
"--HF_TOKEN=HF_{optional token}",
"Qwen/Qwen2-72B-Instruct",
"black-forest-labs/FLUX.1-schnell",
"space/example/specific-endpint"
],
"command": "npx"
}Windows
{
"env": [],
"args": [
"/c",
"npx",
"-y",
"@llmindset/mcp-hfspace",
"--work-dir=~/mcp-files/ or x:/temp/mcp-files/",
"--HF_TOKEN=HF_{optional token}",
"Qwen/Qwen2-72B-Instruct",
"black-forest-labs/FLUX.1-schnell",
"space/example/specific-endpint"
],
"command": "cmd"
}- If ZeroGPU quotas or queues are too long, try duplicating the space. If your job takes less than sixty seconds, you can usually change the function decorator @spaces.GPU(duration=20) in app.py to request less quota when running the job.
- Passing HF_TOKEN will make ZeroGPU quotas apply to your (Pro) HF account
- If you have a private space, and dedicated hardware your HF_TOKEN will give you direct access to that - no quota's apply. I recommend this if you are using for any kind of Production task.
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
