kubrick-api
Add your description here
pinned to #8dc13daupdated 2 weeks ago
Ask your AI client: “install mcps/kubrick-api”.
Requires the metahub MCP server installed in your client. Set up MCP.
mh install mcps/kubrick-apimetahub onboarded this repo on the author's behalf.
If you own github.com/the-ai-merge/multimodal-agents-course on GitHub, claim the listing to take over publishing. Your claim preserves the existing eval history and badges; only the curator label is replaced with verified-publisher on your next publish.
Stars
574
Last commit
2 weeks ago
Latest release
published
- #agent
- #embeddings
- #groq
- #mcp
- #mcp-client
- #mcp-server
- #multimodal
- #openai
- #opik
- #pixeltable
Evaluation report
WarningsAutomated checks the publisher passed at publish time — structure, docs, safety, and whether the artifact behaves as claimed.8dc13da· 2 weeks ago
Documentation
41Description qualitywarn
Only 4 words · 25 chars — more detail helps discovery
Tell consumers what this artifact does in a full sentence.
README is present and substantial
11,981 chars · 12 sections
Tags / topics declared
10 total — agent, embeddings, groq, mcp, mcp-client, mcp-server (+4)
README has usage / example sections
found: Getting Started
Homepage / docs URL declared
no homepage declared (registry will use the repo URL) — info-only, not blocking
Release history
1- releasecurrent8dc13dawarn2 weeks ago
Contents
Welcome to the Kubrick API!
This is the layer that connects it all—exposing the tools and prompts defined by Kubrick MCP and making them accessible through a clean, efficient FastAPI interface.
Kubrick API is one of three core components of the full Kubrick stack (take a peek at the Docker Compose file to see them all), and while it works best with its companions, it can also run solo if needed.
Table of contents
Initial setup
Kubrick API is built with Python and FastAPI, and uses uv for managing dependencies.
1. Install uv
We’re using uv as our Python package manager instead of pip or poetry.
To install uv, simply follow this instructions.
2. Set up your environment
First, create a virtual environment and install the dependencies:
uv venv .venv
# macOS / Linux
. .venv/bin/activate # or source .venv/bin/activate
# Windows
. .\.venv\Scripts\Activate.ps1 # or .\.venv\Scripts\activate
uv pip install -e .
Just to make sure that everything is working, simply run the following command:
uv run python --version
The Python version should be Python 3.12.8.
3. Configure environment variables
You’ll need to set some environment variables. Start by copying the example file:
cp .env.example .env
Then open .env and fill in the required values:
GROQ_API_KEY=
OPIK_API_KEY=
OPIK_PROJECT=kubrick-api
The GROQ_API_KEY is used for the Groq models (Llama 4 Scout and Maverick). The rest are for Opik, our tool for managing everything related to Agent Observability.
Running the API Server
To start things up:
make start-kubrick-api
This command builds the image and spins up the FastAPI container. Once it's up, you can head to:
http://localhost:8000/docs
Here you'll find the interactive API docs, powered by Swagger UI. Great for exploring endpoints and testing things out quickly.
Of course, the API will only work properly if the MCP server is running.
Stopping the API Server
To stop the API server, run:
make stop-kubrick-api
This stops the container and cleans up volumes.
Now that this project is set up, time to go back to the parent README.md!
Reviews
No reviews yet. Be the first.
Related
@remote-mcp/example
@remote-mcp/example MCP server
brainstorm-mcp
MCP server for multi-round AI brainstorming debates across multiple models
vulnerable-mcp-server-malicious-code-exec
A simple MCP server with a get_qotd tool that fetches quotes from a free API
mh install mcps/kubrick-api