# InferMap MCP server

Map messy columns to a known schema — 7 scorers, domain dictionaries, F1 0.84. Zero config.

## Links
- Registry page: https://www.getdrio.com/mcp/io-github-benzsevern-infermap
- Repository: https://github.com/benzsevern/infermap
- Website: https://benzsevern.github.io/infermap/

## Install
- Command: `uvx infermap`
- Endpoint: https://infermap-mcp-production.up.railway.app/mcp/
- Auth: Not captured

## Setup notes
- Package: Pypi infermap v0.4.0
- Remote endpoint: https://infermap-mcp-production.up.railway.app/mcp/

## Tools
- map - Map source columns to target schema using a weighted scorer pipeline with optimal 1:1 assignment. Returns mappings with confidence scores and human-readable reasoning. Endpoint: https://infermap-mcp-production.up.railway.app/mcp/
- inspect - Inspect a data source — show fields, types, sample values, null rates, unique rates, and statistics. Endpoint: https://infermap-mcp-production.up.railway.app/mcp/
- validate - Validate that a source file's columns satisfy a saved mapping config. Reports missing source columns and unmapped required fields. Endpoint: https://infermap-mcp-production.up.railway.app/mcp/
- apply - Apply a saved mapping config to a source CSV, renaming columns according to the mapping and writing the result to an output file. Endpoint: https://infermap-mcp-production.up.railway.app/mcp/

## Resources
Not captured

## Prompts
Not captured

## Metadata
- Owner: io.github.benzsevern
- Version: 0.4.0
- Runtime: Pypi
- Transports: STDIO, HTTP
- License: Not captured
- Language: Not captured
- Stars: Not captured
- Updated: May 11, 2026
- Source: https://registry.modelcontextprotocol.io