Skip to main content
Glama
florenciakabas

xai-toolkit

xai-toolkit

ML model explainability as plain-English narratives, exposed via MCP.

What It Does

Ask a question in VS Code Copilot:

"Why was sample 42 classified as malignant?"

Get back a deterministic English explanation:

"The model classified sample 42 as malignant (probability: 0.91) primarily because of three factors: worst_radius is 2.1× above average (pushing risk up by +0.28), worst_concave_points is elevated (+0.19), and mean_concavity exceeds the norm (+0.14)."

No plots to interpret. No code to run. English that a decision-maker can act on.

Quick Start

uv sync # Install dependencies uv run pytest # Run tests uv run python -m xai_toolkit.server # Start MCP server

Architecture

See AGENTS.md for full project structure and design decisions. See docs/decisions/ for Architecture Decision Records.

Design Principle

The LLM is the presenter, not the analyst. All computation and narrative generation is done deterministically in Python. The LLM chooses the right tool and presents the result — nothing more.

-
security - not tested
F
license - not found
-
quality - not tested

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/florenciakabas/xai-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server