schema_crush_magneto_match – 1 MCP server offers this tool
What it usually takes
candidates– in 1 of 1source– in 1 of 1tier– in 1 of 1
No server marks it as only reading: treat it as able to change data.
From each publisher's own tool list. We never call a tool.
Servers
| Server | Inputs | Read-only? |
|---|---|---|
Schema Crush co.huggingface.teslajoy/schema-crush Match a schema field name against candidates using Magneto structural embeddings. Best for matching field names by structure rather than clinical meaning. Trained on GDC to FHIR mappings. Returns calibrated confidence scores. Requires the optional magneto package, which is not on PyPI. If it is not installed this returns an error explaining how to install it; biobert_match and rule_match work without it. Returns: JSON list of candidates with calibrated confidence scores, best first. | candidates,source,tier | Not stated |