Browse
→ Data & Storage
→ Excel Semantic Normalizer
Excel Semantic Normalizer
Python service and MCP server for normalizing messy procurement or supply-chain spreadsheets. It maps arbitrary Excel headers and column orders into 19 canonical fields using rule matching, hybrid retrieval, optional LLM adjudication, template export, and a human-feedback loop, with an offline fallback when API keys are unavailable. Public GitHub repository created September 5, 2026.
MCP unverified
Integration
| Transport | stdio |
| Auth | none |
| Endpoint | python mcp_server.py |
| Install | git clone https://github.com/climik/excel-normalizer.git && cd excel-normalizer && pip install -r requirements.txt |
Use Cases
| 01 | Normalize vendor spreadsheets with inconsistent headers into typed canonical JSON records |
| 02 | Map columns by semantic meaning rather than position, with confidence scores and issue metadata |
| 03 | Export normalized data back into user-provided Excel templates after MCP-assisted review |
Tags
excel spreadsheets semantic-normalization procurement supply-chain templates python offline
Machine-readable: /api/servers.json
· JSON-LD schema embedded in <head>