SlicerSAFE
A Model Context Protocol server for 3D Slicer integration
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
English | 简体中文
[](https://www.python.org/) [](https://opensource.org/licenses/MIT) [](https://pypi.org/project/mcp-slicer/)
MCP-Slicer connects 3D Slicer with model clients like Claude Desktop or Cline through the Model Context Protocol (MCP), enabling direct interaction and control of 3D Slicer. This integration allows for medical image processing, scene creation, and manipulation using natural language.
Features
- list_nodes: List and filter Slicer MRML nodes and view their properties
- execute_python_code: Execute Python code in the Slicer environment
- capture_screenshot: Capture real-time screenshots of Slicer views
- Full application window (including module panels)
- Individual slice views (Red/Yellow/Green)
- 3D rendering view
- Enables complete REACT loop with visual feedback
Installation
Prerequisites
- 3D Slicer 5.8 or newer
- Python 3.13 or newer
- uv package manager
If you're on Mac, please install uv as
brew install uv
On Windows
powershell -c "irm https://astral.sh/uv/install.ps1 | iex"
and then
set Path=C:\Users\nntra\.local\bin;%Path%
Otherwise installation instructions are on their website: Install uv
⚠️ Please install UV first
Claude for Desktop Integration
Go to Claude > Settings > Developer > Edit Config > claudedesktopconfig.json to include the following:
{
"mcpServers": {
"slicer": {
"command": "ac79ead77a26OBSERVED · 2026-10-08Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control.
claude mcp add mcp-slicer -- uvx mcp-slicer
{
"mcpServers": {
"mcp-slicer": {
"command": "uvx",
"args": [
"mcp-slicer"
]
}
}
}Exposed tools (3)
2 read · 1 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
capture_screenshot | read | Capture a screenshot from 3D Slicer for visual inspection. |
execute_python_code | write | |
list_nodes | read |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- declared (3 observation(s))
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (1)
Gates applied: no_behavioural_pass, no_license.
ac79ead77a26full audit observations/trust-audit/mcp-server/zhaoyouj__slicer.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-08 | ac79ead77a26 | SAFE | B | 89 | first audit |
Questions
What is the Slicer MCP server?
A Model Context Protocol server for 3D Slicer integration
What tools does Slicer expose?
3 in total: 2 read-only, 1 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Slicer safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does Slicer need?
No credential environment variables were found in its source, so it appears to need none.
How current is this page?
The grade is for one exact copy of the source (ac79ead77a26), read on 2026-10-08. The repository is watched and re-audited when it changes.