Xplainable MCP server

Xplainable MCP Server

A Model Context Protocol server for the Xplainable platform. It lets an LLM agent (Claude, or any MCP client) train, deploy, optimise, and explain transparent machine-learning models. The agent is the orchestrator: it inspects the data, decides features and preprocessing, trains, reads the metrics, and iterates.

Training always runs server-side on the Xplainable platform — the MCP host never fits a model locally.

Two Ways to Use It

(OAuth login, no installation).

1. Hosted — connect your MCP client to https://mcp.xplainable.io

key. This is what the rest of this README covers.

1. Local — run the server yourself over stdio with an Xplainable API

Quick Start (Local)

1. Get an API key

Create one at platform.xplainable.io.

2a. Claude Code

claude mcp add xplainable \
  -e XPLAINABLE_API_KEY=your-api-key-here \
  -- uvx --from git+https://github.com/xplainable/xplainable-mcp-server.git xplainable-mcp

2b. Claude Desktop

Add to your MCP settings file:

• macOS: ~/Library/Application Support/Claude/claudedesktopconfig.json
• Windows: %APPDATA%\Claude\claudedesktopconfig.json
• Linux: ~/.config/Claude/claudedesktopconfig.json

{
  "mcpServers": {
    "xplainable": {
      "command": "uvx",
      "args": ["--from", "git+https://github.com/xplainable/xplainable-mcp-server.git", "xplainable-mcp"],
      "env": {
        "XPLAINABLE_API_KEY": "your-api-key-here"
      }
    }
  }
}

No uv? Clone and install instead:

git clone https://github.com/xplainable/xplainable-mcp-server.git
cd xplainable-mcp-server
python -m venv .venv && source .venv/bin/activate
pip install -e .

then use "command": "/path/to/xplainable-mcp-server/.venv/bin/xplainable-mcp" (no args) in the config above.

3. Try it

Ask your agent: "What models and datasets do I have?" — it should call modelslistteammodels and datasetslistteamdatasets.

The Iterate Loop

The tool surface puts the agent in control of every training decision:

deploymentslistdeployments — see the team's assets

1. datasetslistteamdatasets / modelslistteammodels /

and sample rows; decide the target, columns to drop, and whether preprocessing is needed

1. datasetspreviewdatasetjson(datasetid) — inspect columns, types,

preprocessingcreatepreprocessorfromspec → preprocessingpreviewfromdata to verify transformed output 3b. Declare feature relationships once per dataset: datasetsinferrelationships proposes derived columns, implications and monotonic hints with evidence; commit with datasetssetrelationships (re-apply to old versions with modelsapply_relationships)

1. (Optional) preprocessinglistavailable_transformers →

synchronous server-side training; returns model/version IDs, train/test metrics, and feature importances

1. modelstrainmodel(datasetid, targetcolumn, model_name, ...) —

train vs test metrics

1. Inspect: modelsgetfeatureinfo / gptexplain_model; compare

again with different features / preprocessing

1. Iterate: modelsrefitfeatures for per-feature tuning, or train

deploymentsactivatedeployment)

1. deploymentsdeploy(versionid) — deploy once satisfied (then

optimisersrunoptimiser / reportscreatereport (+ poll reportsgetjob_status)

1. Act on the model: inference_predict /

Tool Surface

Tools are generated at server startup from @mcp_tool-decorated methods in the xplainable-client package — there are no checked-in generated files. The surface is flat: every registry tool is exposed, with MCP annotations derived from its category (read → read-only hint, write → destructive hint).

Configuration

Shortened. The full README is on GitHub.