plantcv-mcp

Plant phenotyping over MCP — traits, plus the segmentation overlay they were measured from.

PlantCV as an MCP measurement instrument: it returns plant trait numbers and the picture they were computed from, and refuses to return numbers when the segmentation is degenerate.

Unofficial. Not affiliated with, endorsed by, or sponsored by the Donald Danforth Plant Science Center or the PlantCV maintainers. See NOTICE.

Why you are handed the overlay

Red marks the pixels that were measured, and a cyan line traces the mask's own boundary — the tint alone was invisible on a photo of red beans, so the outline is drawn on the mask's edge pixels and never touches anything unmasked. Both images below come from the same file and the same threshold method — the only difference is one parameter.

✅ channel="a", object_type="dark"	❌ channel="s", object_type="dark"
Mask covers 3.1% of the frame, 9 components. area=32427	Mask covers 96.1% — it is the background. area=1007829

The failure on the right is what this server exists to prevent. Without the picture, both runs return seventeen traits with correct units and entirely believable magnitudes. The one on the right is measuring the wall behind the plants.

segment() returns the overlay and diagnostics but no traits. measure() requires the session_id that segment() mints. You cannot get a number without first being handed the image it came from.

That is not a style preference. Measured on real images with PlantCV 4.11.3:

All three produce correctly-united, entirely believable numbers.

Install

pip install plantcv-mcp

Requires Python 3.11+. Installing pulls PlantCV and its scientific stack, so the first install is not fast. From a checkout: uv add /path/to/plantcv-mcp.

Configure your MCP client

claude mcp add plantcv -- plantcv-mcp

Claude Desktop and other stdio hosts:

{ "mcpServers": { "plantcv": { "command": "plantcv-mcp" } } }

If plantcv-mcp is not on the host's PATH, use "command": "uv", "args": ["run", "--directory", "/path/to/plantcv-mcp", "plantcv-mcp"]. Verify with list_methods(). To confine reads to your imagery: plantcv-mcp --root /data/phenotyping.

Tools

Typical loop: suggest_segmentation → segment → look at the overlay → segment again with a different channel, method or polarity if it is wrong (or refine if it is nearly right) → measure.

The segment() response for the image above — verbatim, apart from a shortened session_id and an elided message — and the overlay arrives beside it as an image:

{
  "session_id": "9d2384c8-…",
  "channel": "a",
  "method": "otsu",
  "object_type": "dark",
  "fill_size": 200,
  "mask_fraction": 0.031,
  "component_count": 9,
  "major_object_count": 4,
  "largest_area": 8628,
  "overlay_scale": 1.0,
  "overlay_png_bytes": 748233,
  "warnings": [
    {
      "code": "multi_specimen",
      "message": "4 comparably-sized objects detected (areas: [8628, 7981, 7106, 6748]). …"
    }
  ]
}

What it refuses, and why

Every guard was calibrated against a real failure and names the next action. Blocking guards withhold numbers; advisories travel with them.

• Inverted mask (implausible_coverage) — the right-hand image above: 96% of the frame selected, seventeen believable traits, all describing the wall.
• Nothing selected, or fill_size deleted the specimen (empty_mask, fill_erased_mask) — PlantCV returns seventeen zeros with in_bounds=True.
• Background texture (noisy_segmentation) — a sorghum photo measured as one 650,000-px plant made of 118 chamber-wall specks.
• Several plants in one mask (multi_specimen) — the number describes the group; use measure_regions(), which measures each plant and numbers the overlay.
• Wrong scale, wrong kind, changed file — a marker measured 4.35× wrong by PlantCV's own ROI method; a thermal session handed to an RGB measurer; an image edited after segmentation. Each is refused naming the right tool.

All 35 warning codes, every tool's parameters, and the measured facts behind each guard: docs/GUIDE.md — segmenting · traits and units · polarity · refining · trays · morphology · batches · hyperspectral and thermal · warning reference.

Security

This server reads image files the host user can read and returns them to the model as images; with no --root there is no allow-list. Run it as a user whose read access you are comfortable exposing, set --root, and do not run it as root. PlantCV/OpenCV analyses run in a worker subprocess, so a native crash is a tool error, not a dead server. Details: security · read roots · crash containment · limitations.

Attribution and licensing

This project is MIT licensed. It depends on PlantCV, which is licensed under the Mozilla Public License 2.0. No PlantCV source is vendored or redistributed here — it is an ordinary runtime dependency — so the MIT license applies to this project's own files. See NOTICE for the full statement.

More

• docs/GUIDE.md — the full guide
• CHANGELOG.md — what changed, and why
• docs/MUTATION-CHECKS.md — every guard disabled on purpose, and the test that went red for it

Images on this page are rendered from tests/fixtures/multi_specimen.png, an original render by the author, and regenerate from committed code.