Xplainable MCP server
Commit Sep 17, 2026Lets an AI agent train, deploy, optimize, and explain transparent machine-learning models via the Xplainable platform.
Also known as xplainable/xplainable-mcp-server
- Stars
- 1
- Tools
- —
- Downloads, 30 days
- —
- Latest version
- 1.0.0
- Last commit
- Sep 17, 2026
- License
- MIT
What is Xplainable MCP?
Xplainable lets an AI agent train, deploy, optimize, and explain transparent machine-learning models via the Xplainable platform.
Summary generated from the project's README
About Xplainable MCP server
Training and managing transparent machine-learning models through an AI agent is what this server enables. It allows developers to use an LLM orchestrator to inspect datasets, decide on preprocessing, and iterate on model performance using the Xplainable platform. Because all training occurs server-side on the Xplainable platform, the local machine hosting the MCP client does not need to fit any models.
Users can connect via a hosted setup using OAuth login or run the server locally via stdio with an XPLAINABLE_API_KEY. The server provides a flat tool surface that includes capabilities for listing team assets, previewing datasets, inferring feature relationships, and deploying models. It supports various configurations including organization or team bindings and allows for custom host overrides for both the platform and inference servers.
This setup is designed for developers who want an agent to handle the heavy lifting of the machine-learning lifecycle. The agent can use tools like models_train_model to execute training, models_get_feature_info to inspect results, and deployments_deploy to push a version to production once satisfied.
What you can do with it
- 1Automated machine learning iterationAsk an agent to inspect a dataset, select features, and train a model to improve metrics.
- 2Explainable model inspectionRequest an explanation of how a specific model makes its decisions.
- 3Managing team machine learning assetsHave an AI client list all available datasets and models within your organization.
- 4Deploying production modelsInstruct the agent to deploy a specific model version once the training metrics are satisfactory.
Written from the project's README. Every use case is checked against a quote from it.
How to install Xplainable MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall Xplainable MCP in Claude Code
$ claude mcp add --transport http xplainable-mcp-server https://mcp.xplainable.io/mcpInstall Xplainable MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"xplainable-mcp-server": {
"url": "https://mcp.xplainable.io/mcp"
}
}
}Install Xplainable MCP in VS Code
.vscode/mcp.json
{
"servers": {
"xplainable-mcp-server": {
"type": "http",
"url": "https://mcp.xplainable.io/mcp"
}
}
}Install Xplainable MCP in VS Code CLI
$ code --add-mcp '{"name":"xplainable-mcp-server","type":"http","url":"https://mcp.xplainable.io/mcp"}'Install Xplainable MCP in Codex
$ codex mcp add xplainable-mcp-server --url https://mcp.xplainable.io/mcpInstall Xplainable MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.xplainable-mcp-server] url = "https://mcp.xplainable.io/mcp"
Install Xplainable MCP in Gemini CLI
$ gemini mcp add -s user --transport http xplainable-mcp-server https://mcp.xplainable.io/mcpInstall Xplainable MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"xplainable-mcp-server": {
"url": "https://mcp.xplainable.io/mcp",
"type": "http"
}
}
}Configuration
XPLAINABLE_API_KEY
| Name | Description | |
|---|---|---|
| XPLAINABLE_API_KEY | — |
Automated checks
Ran Nov 15, 2026Full report →Not verified yet. A server needs a score of 80, no serious finding, and enough data for us to check. How checks work · What to fix for more points
- Source repository linked and reachablexplainable/xplainable-mcp-server is public and reachablegithub.com/xplainable/xplainable-mcp-server ↗Pass
- Package names this repository as its sourceNot checked
- Build provenance (Sigstore attestation)Not checked
- Open source license (OSI)MITspdx.org/licenses/MIT.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-09-17github.com/xplainable/xplainable-mcp-server ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNot checked
- No critical advisory in the package or its dependenciesNot checked
- No hidden instructions to the model0 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNot checked
- Remote endpoint answers the MCP handshakeHTTPS endpoint answered 401 (sign-in required)Pass
README
View on GitHubXplainable 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
- Hosted — connect your MCP client to
https://mcp.xplainable.io(OAuth login, no installation). - 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
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
{
"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
models_list_team_models and datasets_list_team_datasets.
The Iterate Loop
The tool surface puts the agent in control of every training decision:
datasets_list_team_datasets/models_list_team_models/deployments_list_deployments— see the team's assetsdatasets_preview_dataset_json(dataset_id)— inspect columns, types, and sample rows; decide the target, columns to drop, and whether preprocessing is needed- (Optional)
preprocessing_list_available_transformers→preprocessing_create_preprocessor_from_spec→preprocessing_preview_from_datato verify transformed output 3b. Declare feature relationships once per dataset:datasets_infer_relationshipsproposes derived columns, implications and monotonic hints with evidence; commit withdatasets_set_relationships(re-apply to old versions withmodels_apply_relationships) models_train_model(dataset_id, target_column, model_name, ...)— synchronous server-side training; returns model/version IDs, train/test metrics, and feature importances- Inspect:
models_get_feature_info/gpt_explain_model; compare train vs test metrics - Iterate:
models_refit_featuresfor per-feature tuning, or train again with different features / preprocessing deployments_deploy(version_id)— deploy once satisfied (thendeployments_activate_deployment)- Act on the model:
inference_predict/optimisers_run_optimiser/reports_create_report(+ pollreports_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
| Variable | Required | Description |
|---|---|---|
XPLAINABLE_API_KEY |
yes (local) | API key from platform.xplainable.io |
XPLAINABLE_HOST / XPLAINABLE_HOSTNAME |
no | Platform host override (defaults to https://platform.xplainable.io). Set both to the same value. |
XPLAINABLE_INFERENCE_HOST |
no | Inference 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_ID |
no | Org/team binding, if your API key is not bound to a team |
MCP_TRANSPORT |
no | stdio (default) or streamable-http |
LOG_LEVEL |
no | DEBUG, INFO (default), WARNING, ERROR |
See .env.example. The API key is read from the environment only and is never exposed through a tool.
CLI
xplainable-mcp-cli list-tools # list all available tools
xplainable-mcp-cli validate-config # check env configuration
xplainable-mcp-cli test-connection # test API connectivity
xplainable-mcp-cli generate-docs # generate tool documentation
Docker (HTTP mode)
cp .env.example .env # fill in your API key
docker 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
git clone https://github.com/xplainable/xplainable-mcp-server.git
cd xplainable-mcp-server
pip install -e ".[dev]"
pytest # run tests
ruff 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 Server | xplainable-client | fastmcp |
|---|---|---|
| current (main) | >=1.13.0 | >=2.0.0,<3.0.0 |
Contributing
See CONTRIBUTING.md.
License
MIT License — see LICENSE.
Xplainable MCP questions
How do I add Xplainable MCP to Claude Code?
Run claude mcp add --transport http xplainable-mcp-server https://mcp.xplainable.io/mcp in your terminal. Add --scope user to make it available in every project.
How do I add Xplainable MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
Where does the model training actually happen?
Training is performed server-side on the Xplainable platform, meaning the MCP host does not fit the model locally.
How can I use the server locally?
You can run the server locally via stdio using an Xplainable API key.
Can I connect to the hosted version?
Yes, you can connect your MCP client to the hosted service using OAuth login without needing to install anything.