generate_imageLABSCO SUMMARY
One key, eight model tasks.
It is a thin wrapper over DeepInfra with one tool per task, so the choice of model is configuration rather than code, and the tools you never use can be switched off before the client ever sees them.
What it is
An MCP server over DeepInfra's OpenAI-compatible API. Each capability is a separate tool with its own default model, and you decide which of them the server exposes at all.
What you get
- Images generated from a prompt
- Speech transcribed to text
- Text generated against a chat model
- Text classified as a whole, and the tokens inside it labelled
- Images classified against fixed labels, or against labels you supply at call time
- Objects located in an image
Requirements
A DeepInfra API key in DEEPINFRA_API_KEY, and uv to install and run. Each tool's default model is set by its own variable in the .env file, so image generation and transcription can be pointed at different models. Another variable decides which tools appear: give it a comma-separated list to expose only the ones you want.
Setup effort
One command plus a key — uv sync, then supply credentials
USE CASES
01
Getting artwork for a post without leaving the chat
Describe the image and it comes back generated, against whichever model you set as the default.
02
Turning a recorded call into text
Send the audio and get the transcript, using the speech model named in your configuration.
03
Sorting a backlog of support messages by type
Classify each message rather than reading it, and work from the groups that come back.
04
Pulling names and places out of raw text
Token-level labelling marks the entities inside a passage instead of scoring the passage as a whole.
05
Checking a batch of photos against a label you invent on the spot
Zero-shot classification takes the candidate labels at call time, so nothing has to be trained first.
06
Working out what is in a product photo
Locate the objects in the image, then classify the image itself for a single overall answer.
10 tools
Listed in project docs. Your client may show a different list.
text_generationembeddingsspeech_recognitionzero_shot_image_classificationobject_detectionimage_classificationtext_classificationtoken_classificationfill_maskBEFORE YOU INSTALL
What to know first
Tools you get
10 tools named in the project's documentation.
Requires
- uv on PATH
- DEEPINFRA_API_KEY in your environment
Where it runs
The documented client runs the server on your machine.
INSTALLATION
Connect your client
Server setup
TERMINAL
uv syncMCP Clients
Claude Desktop
CLAUDE DESKTOP · JSON
{
"mcpServers": {
"deepinfra": {
"command": "uv",
"args": [
"run",
"mcp_deepinfra"
],
"env": {
"DEEPINFRA_API_KEY": "<YOUR_DEEPINFRA_API_KEY>"
}
}
}
}
