list_available_modelsLABSCO SUMMARY
A detector for your own objects, without leaving the chat.
The expensive part of custom detection is labelling, and that is what gets delegated here: a foundation model does the first pass so YOLOv8 has something to train on. What comes out at the end is a model, not an answer.
What it is
A server that runs an object-detection pipeline end to end from a conversation: you define the classes in plain language, it collects images from Unsplash or a local folder, labels them with a foundation model, then fine-tunes YOLOv8 on the result.
What you get
- Object classes defined in natural language, as the ontology every later step uses (define_ontology)
- Training images downloaded from Unsplash (fetch_unsplash_images) or imported from a folder you already have (import_images_from_folder)
- Automatic labelling of that image set by a foundation model such as GroundedSAM (label_images)
- A custom YOLOv8 detector fine-tuned on your own classes (train_model)
- Supported base and target models listed before you commit, then selected (list_available_models, set_base_model, set_target_model)
- A fixed directory layout, so datasets and runs stay reproducible
Requirements
uv and Python 3.13+, plus an Unsplash API key if you want it to fetch images for you. A CUDA-compatible GPU is recommended for the training step.
Setup effort
Build from source — git clone https://github.com/sensormcp/sensor-mcp
USE CASES
01
Detecting something no off-the-shelf model knows
Describe the classes in words, pick the base model that will label them, and train a detector specific to them.
02
Building a training set from nothing
Images are pulled from Unsplash against your ontology and labelled automatically, so a dataset exists before any manual work starts.
03
Using photographs you already have
Point it at a local folder and the same labelling pass runs over your own images instead of stock ones.
04
Choosing what to build on
The supported base and target models are listed first, so the labelling model and the model being trained are both a deliberate choice.
8 tools
Listed in project docs. Your client may show a different list.
define_ontologyset_base_modelset_target_modelfetch_unsplash_imagesimport_images_from_folderlabel_imagestrain_modelBEFORE YOU INSTALL
What to know first
Tools you get
8 tools named in the project's documentation.
Requires
Python 3.13+
Optional
UNSPLASH_API_KEY in your environment
Where it runs
The documented client runs the server on your machine.
INSTALLATION
Connect your client
Server setup
TERMINAL
git clone https://github.com/sensormcp/sensor-mcp
cd sensor-mcp
uv syncMCP Clients
Any MCP client
ANY MCP CLIENT · JSON
{
"mcpServers": {
"sensormcp-server": {
"type": "stdio",
"command": "uv",
"args": [
"--directory",
"<YOUR_PATH_TO_SENSOR_MCP>",
"run",
"src/zoo_mcp.py"
]
}
}
}The configuration on this page does not set UNSPLASH_API_KEY; the project's instructions put it in a .env file. Check which folder the server reads that file from before you rely on it.
