What it does
Apizr turns existing Python functions into REST APIs or MCP tools. It reads a function without running it, and the user chooses which functions to expose. The generated server runs them when a client calls them.
It suits projects that need to understand a training script or notebook. Apizr produces a report of the data, parameters and calculations found in the source, without training a model or inventing scores. Users can then run trusted code, keep its history, compare results and share a selected prediction function. Optional plugins add tracking of Python calls and Jupyter cells, review in VS Code, project analysis from an MCP client, and building a service image or delivering it with Attest.
It can be installed with uv, pip or Homebrew. The core handles inspection and generation.
Limitations and requirements
Supports Python 3.11 to 3.15 on macOS and Linux. Generated services and experiments should be run only with code and dependencies the user trusts.
Safety
Our team has not reviewed this resource. Only automated rules checked it; resources with high-risk signals are not published. These are signals, not a guarantee that installing it is safe. Try it in a sandbox project first.
- Runs code or changes an assistant's behaviour
Sources
- Official MCP Registry first seen 13 Nov 2026 · last seen 13 Nov 2026 · its page on the source
OuterSpace Apizr
Python capability compiler: read-only analysis, experiment history/comparison and exposure planning.
v0.4.6As shown on registry.modelcontextprotocol.io when we last read it