Metadata-Version: 2.4
Name: ftirfun-mcp
Version: 1.0.0
Summary: FTIR.fun MCP server - FTIR spectral search and material identification for AI agents
Author-email: "FTIR.fun" <ftir.fun@outlook.com>
License: MIT
Project-URL: Homepage, https://ftir.fun
Project-URL: Repository, https://github.com/jxbaoxiaodong/ftirfun
Project-URL: MCP Endpoint, https://ftir.fun/mcp
Project-URL: Server Card, https://ftir.fun/.well-known/mcp/server-card.json
Keywords: ftir,spectroscopy,chemistry,materials,laboratory,mcp,model-context-protocol
Classifier: Development Status :: 5 - Production/Stable
Classifier: Intended Audience :: Science/Research
Classifier: Topic :: Scientific/Engineering :: Chemistry
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Requires-Python: >=3.11
Description-Content-Type: text/markdown
Requires-Dist: mcp>=1.0.0
Requires-Dist: fastapi>=0.115.0
Requires-Dist: uvicorn>=0.20.0
Requires-Dist: numpy>=1.24.0

# FTIR.fun MCP Server

[![PyPI version](https://img.shields.io/pypi/v/ftirfun-mcp.svg)](https://pypi.org/project/ftirfun-mcp/)

MCP (Model Context Protocol) server for FTIR spectral search and material identification.

AI agents can use this server to search FTIR spectral libraries, identify unknown materials from peak lists or spectrum files, and get functional-group assignments.

## Quick Start (Remote HTTP)

```bash
claude mcp add --transport http ftirfun https://ftir.fun/mcp
```

## Tools

| Tool | Description |
|------|-------------|
| `ftir_identify_material` | Identify unknown material from FTIR spectrum |
| `ftir_explain_peaks` | Explain FTIR peaks with peak-group evidence |
| `ftir_match_library_topk` | Return top-k library matches |
| `ftir_assign_functional_groups` | Assign likely functional groups |
| `search` | Search public results (OpenAI-compatible) |
| `fetch` | Fetch result by ID (OpenAI-compatible) |

## Supported File Formats

CSV, TXT, TSV, Excel (.xls/.xlsx), JCAMP-DX (.jdx/.dx), Bruker OPUS (.0~.9), Thermo SPC (.spc), PerkinElmer SPA (.spa), JSON

## Local Installation

```bash
pip install ftirfun-mcp
ftirfun-mcp --help
```

## Links

- Website: https://ftir.fun
- MCP Endpoint: https://ftir.fun/mcp
- Server Card: https://ftir.fun/.well-known/mcp/server-card.json
- Repository: https://github.com/jxbaoxiaodong/ftirfun
