Skip to main content

Vendor-agnostic Model Context Protocol server for multimodal electron microscopy — schema-bound tool layer with pluggable adapters for Gatan, JEOL, Hitachi, …

Project description

nuance-mcp

A library for interfacing with transmission electron microscopes (TEM) via MCP (Model Context Protocol).

Installation

pip install nuance-mcp

Supported Hardware

The package provides adapters for multiple microscope vendors:

  • JEOL: Full support for JEOL JEM-2100F, 2100, 2200FS, 3200FB, 3200, 3400FB, 3400FS, etc.
  • Gatan: Bridge adapter for GMS-EELS and DM (Detector Manager) operations
  • Hitachi: Adapter for Hitachi 2100, 2200, 2700, 2800, 2100II, 2200II, 2100UP, etc.

Usage Examples

JEOL Adapter

from nuance_mcp.adapters.jeol import adapter

mcp = FastMCP("JEOL Adapter")
mcp.add_resource("microscope_state", adapter.get_microscope_state())

Gatan Bridge Adapter

from nuance_mcp.adapters.gatan import adapter

mcp = FastMCP("Gatan Adapter")
mcp.add_resource("eels_data", adapter.get_eels_data())

Hitachi Adapter

from nuance_mcp.adapters.hitachi import adapter

mcp = FastMCP("Hitachi Adapter")
mcp.add_resource("stem_image", adapter.acquire_stem())

Features

  • Multi-vendor support: Works with JEOL, Gatan, and Hitachi systems
  • Image acquisition: TEM, STEM, 4D-STEM imaging
  • Spectrum acquisition: EELS data collection
  • Diffraction: SAD/HRTEM patterns
  • Detector control: CCD, direct detection cameras
  • Image processing: Filters, FFT analysis, spot mapping, DPC
  • Stage control: X/Y positioning, tilting series
  • Live processing: Job submission and monitoring

Supported Capabilities

The following capabilities are supported by JEOL adapters:

  • TEM/STEM: Conventional and annular dark field imaging
  • EELS/EDS: Spectroscopy data acquisition
  • FFT/DPC: Fourier transform and differential phase contrast processing
  • Image filters: Radial profiles, spot mapping
  • Live jobs: Asynchronous data processing

Academic Citation

If you use this work or its concepts in your research, please cite our associated preprint:

Title: Schema-Bound LLM Control of Scientific Instrumentation through Model Context Protocol Skills
Authors: Roberto dos Reis, Vinayak P. Dravid
(arXiv ID and URL pending)

@misc{dosReis2026SchemaBound,
  title={Schema-Bound LLM Control of Scientific Instrumentation through Model Context Protocol Skills},
  author={Roberto dos Reis and Vinayak P. Dravid},
  year={2026},
  eprint={PENDING},
  archivePrefix={arXiv}
}

Intellectual Property Disclosure

This software, schemas, and the associated methodologies for agentic control of scientific instrumentation using the Model Context Protocol (MCP) were developed in whole or in part at Northwestern University.

This work is the subject of the following Northwestern University Invention Disclosure:

  • Disclosure Title: Universal Control Protocol for Scientific Instrumentation Using Extended Model Context Protocol
  • Invention ID: Disc-ID-25-05-22-002
  • Tech ID: 2025-136
  • Inventors: Roberto Moreno Souza dos Reis, Vinayak P. Dravid

Commercialization, licensing inquiries, and related intellectual property matters should be directed to the Innovation and New Ventures Office (INVO) at Northwestern University.

License

MIT

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

nuance_mcp-0.2.0.tar.gz (43.2 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

nuance_mcp-0.2.0-py3-none-any.whl (47.9 kB view details)

Uploaded Python 3

File details

Details for the file nuance_mcp-0.2.0.tar.gz.

File metadata

  • Download URL: nuance_mcp-0.2.0.tar.gz
  • Upload date:
  • Size: 43.2 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.10.9

File hashes

Hashes for nuance_mcp-0.2.0.tar.gz
Algorithm Hash digest
SHA256 bed537e5b4bf1fc30d4fa737f0ec404bce2175727bb90326aba0678c10c95993
MD5 a9e8e5993ed2fe687d1ac085a035d3bd
BLAKE2b-256 1689ada0fdfddb24d0db8f6900fff64593581e47bcb609937df9125ec9fc5261

See more details on using hashes here.

File details

Details for the file nuance_mcp-0.2.0-py3-none-any.whl.

File metadata

  • Download URL: nuance_mcp-0.2.0-py3-none-any.whl
  • Upload date:
  • Size: 47.9 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.10.9

File hashes

Hashes for nuance_mcp-0.2.0-py3-none-any.whl
Algorithm Hash digest
SHA256 7cffd8bef453c59cdecf0b5733d7d24606544242e2791a6b02808670585b1efc
MD5 da242927995de73e5752a9e6504c48fe
BLAKE2b-256 7fa8f3019333785ed370ac90ea150a429ff84522c0edce2023fe942608b1e382

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page