Skip to main content

carrot-mcp-sys

Carrot MCP System Server — screenshot capture for multimodal analysis.

Features

  • Multi-monitor support: Capture individual monitors or all at once
  • Region capture: Crop to any rectangular area using absolute screen coordinates
  • Save to file: Optionally save captured images to disk
  • MCP-compatible output: Returns base64-encoded PNG images ready for LLM processing

Tools

Tool Description
version Get server version info
list_monitors List all monitors with coordinates and resolution
screenshot Capture screenshot — supports monitor index, region coordinates, or all monitors

Installation

# From project root
uv sync --all-packages

# Or install standalone
pip install carrot-mcp-sys

Usage

Run as MCP server

carrot-mcp sys
python -m carrot_mcp_sys

Coordinate system

All coordinates are absolute screen pixels with origin (0,0) at the top-left corner of the virtual screen.

Monitor 1 (left):  left=0,    top=0, width=1920, height=1080
Monitor 2 (right): left=1920, top=0, width=2560, height=1440

Use list_monitors to discover each monitor's position.

Examples

Capture full monitor:

{"tool": "screenshot", "monitor": 1}

Capture an absolute region:

{"tool": "screenshot", "left": 1920, "top": 100, "width": 800, "height": 600}

Capture all monitors:

{"tool": "screenshot"}

Save to file:

{"tool": "screenshot", "monitor": 1, "save_path": "/tmp/capture.png"}

Output format

Returns list[TextContent | ImageContent]:

  • First element: JSON metadata with status, timestamp, and monitors dict (keyed by monitor index)
  • Remaining elements: One ImageContent per captured monitor (PNG image)

Example response structure:

[
  {
    "type": "text",
    "text": {
      "status": "ok",
      "timestamp": "2026-07-01T07:38:55.105440+00:00",
      "monitors": {
        "1": {
          "width": 1920, "height": 1080,
          "origin": {"left": 0, "top": 0},
          "bytes": 120887,
          "monitor": {"index": 1, "left": 0, "top": 0, "width": 1920, "height": 1080}
        }
      }
    }
  },
  {
    "type": "image",
    "data": "<base64 PNG>",
    "mimeType": "image/png"
  }
]

Dependencies

  • mcp>=1.28.0
  • mss>=9.0.0 — fast cross-platform screenshot library

Metadata

Release files for carrot-mcp-sys 0.1.2

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for carrot-mcp-sys 0.1.2
File Size Uploaded Provenance Actions
carrot_mcp_sys-0.1.2.tar.gz 3.5 kB Without provenance Details for carrot_mcp_sys-0.1.2.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for carrot-mcp-sys 0.1.2
File Interpreter ABI Platform Actions
carrot_mcp_sys-0.1.2-py3-none-any.whl Python 3 none any Details for carrot_mcp_sys-0.1.2-py3-none-any.whl

Total release size: 8.1 kB

Release files / carrot_mcp_sys-0.1.2.tar.gz

Download URL carrot_mcp_sys-0.1.2.tar.gz
Size 3.5 kB
Tags Source
SHA-256 checksum
How to use checksums
10f16571ace2cbfed41dcc6386a39ef830e9ae5ac7984b36ce896df9cedab645
BLAKE2b-256 checksum
How to use checksums
4aae136acfaed64db8114f94a991b49c14fa2cae43c0e290ac13aa71c505c06c
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.13.14

Release files / carrot_mcp_sys-0.1.2-py3-none-any.whl

Download URL carrot_mcp_sys-0.1.2-py3-none-any.whl
Size 4.6 kB
Tags Python 3
SHA-256 checksum
How to use checksums
d93ec420be29121949b0b012ccc3bad9f692aae2aecd0cc179860fa5341fe270
BLAKE2b-256 checksum
How to use checksums
3e8de89e7d35323acda7f1c243c6c5ad160ea9198271e953dfa87d5389a43d92
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.13.14

Security for carrot-mcp-sys 0.1.2

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page