# Micro-Manager Microscope (pypi · labmcp-micro-manager)

MCP server for microscopes controlled by Micro-Manager (pymmcore-plus).

- Trust score: 69/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-30

## Components

- pypi · `labmcp-micro-manager`: 69/100 (this document), [markdown](https://verifymcp.io/servers/k-dense-ai-labmcp-micro-manager/labmcp-micro-manager.md), [page](https://verifymcp.io/servers/k-dense-ai-labmcp-micro-manager/labmcp-micro-manager)

## Channel facts

- Registry: `pypi`
- Package: `labmcp-micro-manager`
- Version: `0.1.3`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-09-30.

- **Supply Chain Security**: 49/100
  - Malware scan not yet available for this package.
  - No known CVEs affecting this package version or its production dependencies.
  - Runs hatchling.build at install time, a recognised build step with no custom scripting around it.
  - 4 of 34 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 100/100
  - Source repository is publicly reachable at the declared URL.
  - Cryptographically verified build provenance (signed, bound to K-Dense-AI/lab-instrument-mcps).
  - Clear OSI-approved license (Apache-2.0).
  - Actively maintained (last published 3 days ago).
  - Publishes a security disclosure policy (SECURITY.md).
- **Schema Quality & AI Usability**: 78/100
  - AI-judged instruction clarity (excellent).
  - Tool/resource definitions use about 1769 tokens (~93/item across 19 items; 19 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 17/100
  - Stability observed for 5 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 99/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 97% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 19 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 20 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

## Install

### How do I install the Micro-Manager Microscope MCP server?

Micro-Manager Microscope runs locally as a PyPI package, launched with uvx labmcp-micro-manager. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add k-dense-ai-labmcp-micro-manager -- uvx labmcp-micro-manager
```

### Cursor

```json
{
  "mcpServers": {
    "k-dense-ai-labmcp-micro-manager": {
      "command": "uvx",
      "args": [
        "labmcp-micro-manager"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "k-dense-ai-labmcp-micro-manager": {
      "command": "uvx",
      "args": [
        "labmcp-micro-manager"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add k-dense-ai-labmcp-micro-manager -- uvx labmcp-micro-manager
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "k-dense-ai-labmcp-micro-manager": {
      "type": "local",
      "command": [
        "uvx",
        "labmcp-micro-manager"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add k-dense-ai-labmcp-micro-manager --command uvx --arg labmcp-micro-manager
```

### Hermes

```yaml
mcp_servers:
  k-dense-ai-labmcp-micro-manager:
    command: "uvx"
    args: ["labmcp-micro-manager"]
```

### Netclaw

```json
{
  "McpServers": {
    "k-dense-ai-labmcp-micro-manager": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "labmcp-micro-manager"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add k-dense-ai-labmcp-micro-manager -t stdio -c uvx -a labmcp-micro-manager
```

### Other

```json
{
  "mcpServers": {
    "k-dense-ai-labmcp-micro-manager": {
      "command": "uvx",
      "args": [
        "labmcp-micro-manager"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-09-30 (score 69, +1)

No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-28 (score 68, +29)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-09-27 (score 39, 0)

- [functional] Package version: 0.1.2 → 0.1.3

### 2026-09-26 (score 39, −17)

- [security regression] Tool safety: pass → unverified
- [security improvement] Malware scan: unverified → pass
- [security] Stability: Stability not yet verified: we do not have a sandbox capture of the MCP schema this version of the package serves yet.
- [functional regression] Capabilities: pass → unverified
- [functional regression] Tool coverage: 100 → unverified
- [functional improvement] Stability: unverified → 0.03
- [functional] First check of Schema quality: unverified
- [functional] Package version: 0.1.0 → 0.1.2
- [functional] Package version: 0.1.0 → 0.1.1

### 2026-09-25 (score 56)

First indexed and scored.

## MCP tools (19)

### `get_connection_info` (~40 tokens)

Get Connection Info

Report which instrument is connected (identity, address, simulated or real),
whether the server is read-only, and the active safety limits. Call this first.

### `get_command_log` (~46 tokens)

Get Command Log

Return the most recent raw commands sent to / replies received from the
instrument (newest last). Useful for debugging and for recording what was done.

Input parameters:

- `limit` (integer)

Output parameters:

- `result` (array)

### `reconnect` (~35 tokens)

Reconnect

Close and re-open the connection to the instrument (e.g. after it was power
cycled or a cable was re-plugged).

### `get_system_info` (~64 tokens)

Get System Info

Describe the microscope: loaded devices (camera, stages, shutters, filter wheels...), which
device has which role, camera size/bit depth/exposure, pixel size, config groups with their
presets, the current position, and the soft limits. Call this first.

Output parameters:

- `auto_shutter` (boolean)
- `autofocus`
- `bit_depth`
- `camera`
- `config_groups` (array)
- `configuration` (string)
- `devices` (array)
- `exposure_ms`
- `focus`
- `image_height_px`
- `image_width_px`
- `mmcore_version` (string)
- `pixel_size_um`: Calibrated pixel size for the current objective, if configured
- `position` (object)
- `shutter`
- `shutter_open`
- `soft_limits_um` (object)
- `timestamp` (string)
- `xy_stage`

### `list_config_groups` (~33 tokens)

List Config Groups

List Micro-Manager config groups (e.g. Channel, Objective) with their presets and the preset
currently active.

Output parameters:

- `result` (array)

### `set_config` (~80 tokens)

Set Config

Apply a config-group preset (e.g. switch the channel: filter cube, light source, emission
filter). Objective/turret groups are refused here: use `set_objective`.

Input parameters:

- `group` (string, required): Config group, e.g. 'Channel'
- `preset` (string, required): Preset in that group, e.g. 'FITC'

Output parameters:

- `current`
- `name` (string)
- `presets` (array)
- `role`: 'channel', 'objective' or None

### `set_objective` (~82 tokens)

Set Objective

Switch the objective (rotates the nosepiece/turret). A longer or immersion objective can hit the
sample holder or need oil/water: confirm with the user first. Pixel size changes with the objective.

Input parameters:

- `group`: Objective config group; default: auto-detected
- `preset` (string, required): Objective preset, e.g. '20x'

Output parameters:

- `current`
- `name` (string)
- `presets` (array)
- `role`: 'channel', 'objective' or None

### `get_exposure` (~17 tokens)

Get Exposure

Return the camera exposure time in milliseconds.

Output parameters:

- `result` (number)

### `set_exposure` (~49 tokens)

Set Exposure

Set the camera exposure time (ms). Longer exposures give brighter images but more
photobleaching. Returns the exposure the camera accepted.

Input parameters:

- `exposure_ms` (number, required): Camera exposure time in ms

Output parameters:

- `result` (number)

### `set_shutter` (~79 tokens)

Set Shutter

Open or close the current shutter, and optionally switch auto-shutter. An open shutter
illuminates (and bleaches) the sample until it is closed again.

Input parameters:

- `auto_shutter`: Also set auto-shutter (open only during exposures). Leave on normally.
- `open` (boolean, required): True opens the shutter (sample illuminated continuously)

### `close_shutter` (~24 tokens)

Close Shutter

Close the shutter (stop illuminating the sample) and abort any running acquisition.

### `get_position` (~34 tokens)

Get Position

Read the XY stage and focus (Z) positions in micrometres, and which way increasing Z moves
the objective.

Output parameters:

- `focus`
- `focus_direction` (string): What increasing Z does: 'toward_sample', 'away_from_sample' or 'unknown'
- `timestamp` (string)
- `x_um`
- `xy_stage`
- `y_um`
- `z_um`

### `move_stage_xy` (~107 tokens)

Move Stage Xy

Move the XY stage. Moves longer than `max_xy_step_um` or outside the XY soft limits are refused
before anything moves. Make sure the objective and condenser clear the sample holder.

Input parameters:

- `relative` (boolean): Interpret x_um/y_um as offsets from the current position
- `x_um` (number, required): Target X (µm), or the X offset if relative=True
- `y_um` (number, required): Target Y (µm), or the Y offset if relative=True

Output parameters:

- `moved_um` (number): Distance moved
- `timestamp` (string)
- `toward_sample`: For Z moves: True if the objective moved toward the sample
- `x_um`
- `y_um`
- `z_um`

### `move_z` (~87 tokens)

Move Z

Move the focus drive (Z). Moving the objective toward the sample can crash it into the slide:
moves larger than `max_z_step_um` or outside the Z soft limits are refused before anything moves.

Input parameters:

- `relative` (boolean): Interpret z_um as an offset from the current position
- `z_um` (number, required): Target focus position (µm), or the offset if relative=True

Output parameters:

- `moved_um` (number): Distance moved
- `timestamp` (string)
- `toward_sample`: For Z moves: True if the objective moved toward the sample
- `x_um`
- `y_um`
- `z_um`

### `stop_stage` (~27 tokens)

Stop Stage

Immediately stop XY and Z stage motion and abort any z-stack or time-lapse in progress.

### `autofocus` (~52 tokens)

Autofocus

Run the configured autofocus device (e.g. a hardware focus lock) once; it moves the focus drive.
If the result is outside the Z step or soft limits, the focus is moved back and an error is raised.

Output parameters:

- `moved_um` (number): Distance moved
- `timestamp` (string)
- `toward_sample`: For Z moves: True if the objective moved toward the sample
- `x_um`
- `y_um`
- `z_um`

### `snap_image` (~110 tokens)

Snap Image

Acquire one image with the current channel, exposure and position. The sample is illuminated
during the exposure. Saves the full image as TIFF and returns summary statistics (min/max/mean,
saturation, sharpness) plus an optional contrast-stretched preview.

Input parameters:

- `include_preview` (boolean): Return a small PNG preview image
- `preview_size_px` (integer): Longest side of the preview
- `save_path`: TIFF path for the full image; default: a timestamped file in data_dir

Output parameters:

- `bit_depth` (integer)
- `dtype` (string)
- `exposure_ms` (number)
- `focus_score` (number): Sharpness (normalised gradient energy); compare within one field
- `height_px` (integer)
- `max` (number)
- `mean` (number)
- `min` (number)
- `path` (string): TIFF file with the full image
- `pixel_size_um`
- `presets` (object): Current preset of every config group
- `saturated_fraction` (number): Fraction of pixels at the camera's maximum value
- `std` (number)
- `timestamp` (string)
- `warning`
- `width_px` (integer)
- `x_um`
- `y_um`
- `z_um`

### `acquire_z_stack` (~207 tokens)

Acquire Z Stack

Acquire a z-stack around the current focus: moves Z through the slices (optionally imaging
several channels at each), saves a multi-page TIFF, reports per-slice statistics and the sharpest
slice, and returns Z to where it started. Every slice must stay within `max_z_step_um` of the start
and the Z soft limits.

Input parameters:

- `channel_group`: Config group of the channels; default: channel group
- `channels`: Channel presets to image at every slice; omit for current settings
- `end_offset_um` (number, required): Last slice relative to the current Z (e.g. +10)
- `include_preview` (boolean): Return a max-intensity projection preview
- `save_path`: Multi-page TIFF path (ImageJ hyperstack, ZCYX)
- `start_offset_um` (number, required): First slice relative to the current Z (e.g. -10)
- `step_um` (number, required): Spacing between slices (µm)

Output parameters:

- `aborted` (boolean)
- `axes` (string): Axis order of the TIFF, e.g. 'ZCYX'
- `best_focus_z_um`: Z of the sharpest slice (first channel)
- `channels` (array)
- `duration_s` (number)
- `frames` (array)
- `note`: Why the acquisition ended early, if it did
- `path` (string)
- `returned_to_z_um`
- `shape` (array)
- `timestamp` (string)
- `z_positions_um` (array)

### `acquire_time_lapse` (~172 tokens)

Acquire Time Lapse

Acquire a time-lapse at the current position: images every `interval_s` (optionally several
channels per timepoint), saves a multi-page TIFF and reports per-frame statistics and the intensity
change (bleaching). Bounded by `max_frames` and `max_acquisition_duration_s`; `stop_stage` aborts it.

Input parameters:

- `channel_group`: Config group of the channels; default: channel group
- `channels`: Channel presets to image at every timepoint; omit for current settings
- `include_preview` (boolean): Return a preview of the last frame
- `interval_s` (number, required): Time between timepoint starts (s)
- `save_path`: Multi-page TIFF path (ImageJ hyperstack, TCYX)
- `timepoints` (integer, required): Number of timepoints

Output parameters:

- `aborted` (boolean)
- `axes` (string)
- `channels` (array)
- `duration_s` (number)
- `frames` (array): Per-frame statistics (at most 100 evenly spaced frames)
- `intensity_change_percent` (object): Mean intensity change from first to last timepoint per channel (bleaching/drift indicator)
- `interval_s` (number)
- `note`: Why the acquisition ended early, if it did
- `path` (string)
- `shape` (array)
- `timestamp` (string)

## Diagnostics

Captured diagnostic sections: Provenance, Install scripts, Dependencies. The full working is on the page: https://verifymcp.io/servers/k-dense-ai-labmcp-micro-manager/labmcp-micro-manager#diagnostics

## Score history

- 2026-09-30: 69
- 2026-09-29: 68
- 2026-09-28: 68
- 2026-09-27: 39
- 2026-09-26: 39
- 2026-09-25: 56

## Common questions

### What is the Micro-Manager Microscope MCP server?

Micro-Manager Microscope is an MCP server listed in the public MCP registry as io.github.K-Dense-AI/labmcp-micro-manager. MCP server for microscopes controlled by Micro-Manager (pymmcore-plus). This page covers its PyPI package (labmcp-micro-manager).

### Is the Micro-Manager Microscope MCP server safe to use?

Micro-Manager Microscope scores 69 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 30 September 2026. Its build provenance is signed and verified. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the Micro-Manager Microscope MCP server expose?

Micro-Manager Microscope exposes 19 tools: get_connection_info, get_command_log, reconnect, get_system_info, list_config_groups, and 14 more. Their descriptions and schemas cost roughly 1,345 tokens of context every time the server is loaded.

### Is the Micro-Manager Microscope MCP server still maintained?

Micro-Manager Microscope is still listed as active in the MCP registry. We last reached this channel on 30 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What licence is the Micro-Manager Microscope MCP server under?

Micro-Manager Microscope declares the Apache-2.0 licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

## Links

- PyPI project: https://pypi.org/project/labmcp-micro-manager/
- Socket report: https://socket.dev/pypi/package/labmcp-micro-manager
- Repository: https://github.com/K-Dense-AI/lab-instrument-mcps
- Website: https://github.com/K-Dense-AI/lab-instrument-mcps/tree/main/servers/biology/micro-manager
- Changelog RSS feed: https://verifymcp.io/servers/k-dense-ai-labmcp-micro-manager/labmcp-micro-manager.xml
- Changelog JSON feed: https://verifymcp.io/servers/k-dense-ai-labmcp-micro-manager/labmcp-micro-manager.json
- HTML version of this page: https://verifymcp.io/servers/k-dense-ai-labmcp-micro-manager/labmcp-micro-manager