Xplainable Mcp Server

io.github.xplainablePublished by GitHub account xplainablev1.0.0Updated Oct 24, 2026

Train, explain, optimise and deploy transparent glass-box ML models via workflow tools.

VerifiedStreamable HTTPWeb executableData & AnalyticsAI & ML

Overview

AI-generated overview

Connects an assistant to the Xplainable platform to train, explain, optimise and deploy transparent glass-box machine-learning models.

What you can do
  • List and preview team datasets and models, including columns, types and sample rows
  • Create and preview preprocessing transformers, and infer or set feature relationships
  • Train models server-side and read train/test metrics and feature importances
  • Inspect and explain models, refit individual features, and iterate on training
  • Deploy and activate model versions, then run predictions, optimisers and reports
When to use it
Use it when you want an assistant to drive the full modelling loop on Xplainable: inspect data, choose features and preprocessing, train and compare transparent models, explain them, and deploy the result. It suits teams already using the Xplainable platform rather than one-off local experiments.
Requirements
A remote endpoint at mcp.xplainable.io with OAuth login, or a local install run over stdio with an Xplainable API key from the platform. The local option needs Python with uvx or a cloned repository; optional variables override the platform host, inference host, org/team binding, transport and log level.
Before you install
Training, deployment, inference, optimiser runs and report creation act on your team's platform account and change server-side state; deployments and activations affect live models. The local mode requires an XPLAINABLE_API_KEY, which is read from the environment. Datasets and model data are sent to the Xplainable platform for training.

Installation

In SourceWeft

  1. Open Xplainable Mcp Server in the dashboard and add it to a workspace.
  2. Connect the required credentials. They are stored privately and never shown on public pages.
  3. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/io.github.xplainable%2Fxplainable-mcp-server/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config. The client completes OAuth sign-in on first connect.

{
  "mcpServers": {
    "xplainable": {
      "type": "http",
      "url": "https://mcp.xplainable.io/mcp"
    }
  }
}

README

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

  1. Hosted — connect your MCP client to https://mcp.xplainable.io (OAuth login, no installation).
  2. Local — run the server yourself over stdio with an Xplainable API key. This is what the rest of this README covers.

Quick Start (Local)

1. Get an API key

Create one at platform.xplainable.io.

2a. Claude Code

bash
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/claude_desktop_config.json
  • Windows: %APPDATA%\Claude\claude_desktop_config.json
  • Linux: ~/.config/Claude/claude_desktop_config.json
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:

bash
git clone https://github.com/xplainable/xplainable-mcp-server.gitcd xplainable-mcp-serverpython -m venv .venv && source .venv/bin/activatepip 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 models_list_team_models and datasets_list_team_datasets.

The Iterate Loop

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

  1. datasets_list_team_datasets / models_list_team_models / deployments_list_deployments — see the team's assets
  2. datasets_preview_dataset_json(dataset_id) — inspect columns, types, and sample rows; decide the target, columns to drop, and whether preprocessing is needed
  3. (Optional) preprocessing_list_available_transformers → preprocessing_create_preprocessor_from_spec → preprocessing_preview_from_data to verify transformed output 3b. Declare feature relationships once per dataset: datasets_infer_relationships proposes derived columns, implications and monotonic hints with evidence; commit with datasets_set_relationships (re-apply to old versions with models_apply_relationships)
  4. models_train_model(dataset_id, target_column, model_name, ...) — synchronous server-side training; returns model/version IDs, train/test metrics, and feature importances
  5. Inspect: models_get_feature_info / gpt_explain_model; compare train vs test metrics
  6. Iterate: models_refit_features for per-feature tuning, or train again with different features / preprocessing
  7. deployments_deploy(version_id) — deploy once satisfied (then deployments_activate_deployment)
  8. Act on the model: inference_predict / optimisers_run_optimiser / reports_create_report (+ poll reports_get_job_status)

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

VariableRequiredDescription
XPLAINABLE_API_KEYyes (local)API key from platform.xplainable.io
XPLAINABLE_HOST / XPLAINABLE_HOSTNAMEnoPlatform host override (defaults to https://platform.xplainable.io). Set both to the same value.
XPLAINABLE_INFERENCE_HOSTnoInference server override for the direct-to-inference tools (inference_score_dataset, optimisers_run_portfolio); defaults to https://inference.xplainable.io. Set it whenever the platform host is non-prod.
XPLAINABLE_ORG_ID / XPLAINABLE_TEAM_IDnoOrg/team binding, if your API key is not bound to a team
MCP_TRANSPORTnostdio (default) or streamable-http
LOG_LEVELnoDEBUG, INFO (default), WARNING, ERROR

See .env.example. The API key is read from the environment only and is never exposed through a tool.

CLI

bash
xplainable-mcp-cli list-tools            # list all available toolsxplainable-mcp-cli validate-config       # check env configurationxplainable-mcp-cli test-connection       # test API connectivityxplainable-mcp-cli generate-docs         # generate tool documentation

Docker (HTTP mode)

bash
cp .env.example .env   # fill in your API keydocker compose up --build

The container serves streamable-HTTP on port 8000 with a /health endpoint. For anything beyond localhost, terminate TLS at a reverse proxy.

Development

bash
git clone https://github.com/xplainable/xplainable-mcp-server.gitcd xplainable-mcp-serverpip install -e ".[dev]"
pytest            # run testsruff check .      # lint

Runtime tool generation

Client-backed tools are generated at import time by xplainable_mcp/runtime_tools.py from the @mcp_tool registry in xplainable-client — there is no sync step. Upgrading the pinned xplainable-client version is all it takes to pick up new or changed tools; the test suite (tests/test_surface.py) pins the tool count so surface changes are always deliberate.

Compatibility

MCP Serverxplainable-clientfastmcp
current (main)>=1.13.0>=2.0.0,<3.0.0

Contributing

See CONTRIBUTING.md.

License

MIT License — see LICENSE.

Source: README.md at commit eeba577

Tools

0
This server asks you to sign in, so SourceWeft could not read its tools without an account and has not indexed them. What a connected account sees can depend on that account and its permissions.

Version history

1
  1. v1.0.0LatestSep 16, 2026

Score

85% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts