The Team
Built by researchers,
for researchers.
MedMCP is an agentic system that runs state-of-the-art medical imaging pipelines from a familiar chat interface. No terminal, no code, just plain language.
Demo
A short walkthrough of the workspace and its current capabilities, from a plain-language request to finished, inspectable results.
Use plain language, the same way you'd explain it to a colleague. No commands, environment management, or programming experience needed.
MedMCP selects the right tools, sequences them, and handles all the technical details automatically.
Before MedMCP touches your data, you see exactly what is about to happen. Approve or reject with a single click. You always stay in full control.
The Agentic System
MedMCP is an agent, not a chatbot. It reasons about your goal, sequences the right tools, executes them under your control, and keeps a complete record of everything it did.
From one plain-language goal, it sequences the whole chain (DICOM conversion, skull-stripping, registration, segmentation) in the correct order.
It orchestrates trusted, published methods. Nothing is generated at runtime. The intelligence plans; proven tools execute.
Every file operation and tool call is shown for review first. Nothing touches your data until you approve it.
Every approved and rejected action is logged to an append-only record: a complete, reproducible trail of what ran on your data and when.
Distill any session into a deterministic, replayable pipeline. Run it again on new patients with no model in the loop. The same steps every time.
Bind one workflow to a folder of subjects and process an entire cohort in a single run, with failures isolated per subject and progress streamed live.
Who It's For
In the clinic and in the lab, MedMCP makes the field's best imaging tools available to the people who should use them.
Run validated segmentation, registration, and lesion analysis on your own patients.
Skip the Python environments and DICOM wrangling, and batch a whole cohort in one request.
Privacy & Safety
MedMCP was designed for clinical and translational research environments, where data governance is non-negotiable.
The AI model runs on your hardware. No imaging data, patient metadata, or results are ever sent to a cloud service.
Every file operation, every analysis step, every tool call is shown to you before it runs. You stay in full control.
After installation, MedMCP does not need an active internet connection to run analyses.
Every approved and rejected action is logged persistently, giving you a complete record of what ran on your data and when.
Always Getting Better
MedMCP is built around open-weight models (Muse Glimmer today). However, nothing ties it to a single model. As stronger open models are released, you can move to them and the whole system improves with no extra work on your side.
What requires a frontier cloud model today will soon run on your local hardware. MedMCP is built to make the most of each new generation.
The model and the tools stay separate. Your imaging pipelines are validated once and always behave the same way; a more capable model simply gets better at choosing and running them.
Our Vision
"The tools exist. The methods work. What is missing is the infrastructure to put them in the hands of the people who are best positioned to use them. MedMCP exists to close that gap."
We believe that one of the biggest problems in medical image analysis is the systematic disconnect between well-working tools and the people who need them. No clinician or researcher should need a software engineer to run these pipelines. Our goal is simple: make the field's best methods usable by anyone who needs them, reliably and safely, on their own infrastructure.
Capability Stacks
MedMCP's capabilities are organized into domain stacks. Activate one and its tools appear automatically in the workspace, ready for the agent to plan with. All of this is work in progress: the first stacks are available, they keep evolving, and new ones land regularly.
DICOM discovery, NIfTI conversion, and BIDS organisation. The foundation layer every other stack builds on.
Brain extraction (HD-BET), image registration (ANTs), and whole-brain segmentation (FastSurfer).
Multiple sclerosis white-matter lesion segmentation and lesion load (LST-AI).
Whole-body segmentation of over 100 anatomical structures in CT and MR images (TotalSegmentator).
Clinical cohort assembly, imaging-biomarker stratification, and association analysis (ehrapy).
Spinal cord segmentation, cross-sectional area, and lesion metrics for spine imaging workflows.
Cardiac structure segmentation and functional analysis for echocardiography and cardiac MRI workflows.
Cell detection, tissue segmentation, and quantification pipelines for digital pathology and microscopy images.
The Team
Get involved
MedMCP is built in the open, and all of it is work in progress. New tools, new stacks, bug reports, and ideas are all welcome. Reach out for a demo or a chat, or jump straight into the code.