AlbumentationsX MCP

io.github.dKosarevskyPublished by GitHub account dKosarevskyv1.21.1Updated Nov 3, 2026

AlbumentationsX MCP for batch previews, compare preview runs, segmentation masks, and exports.

VerifiedSTDIODesktop onlyData & AnalyticsMedia & DesignAI & ML

Overview

AI-generated overview

Local MCP server for AlbumentationsX that lets an assistant inspect image datasets, preview augmentation batches, compare runs, and export pipelines.

What you can do
  • Discover transforms, inspect schemas and recipes, and validate augmentation pipelines
  • Run deterministic batch previews with contact sheets and annotation overlays for classification, detection, segmentation, OCR, bbox, mask and keypoint data
  • Compare, rank and report on preview runs, and trace a specific variant back to its settings
  • Collect structured feedback and tuning sessions to refine augmentation choices
  • Export accepted pipelines as Python, JSON or YAML, with CPU torch.Tensor validation and a guarded Python handoff
  • Run host smoke checks and environment diagnostics
When to use it
Useful when you want an assistant to help tune image augmentation for a dataset: trying robustness variants, visually reviewing batch previews, rejecting settings that look wrong, and exporting a reproducible pipeline. It suits computer-vision and ML data-preparation work rather than general image editing.
Requirements
Runs locally over stdio, installed from the albumentationsx-mcp PyPI package (for example via uvx) or as a Claude Desktop extension bundle. Needs local image directories passed as an allowed root and an artifact directory for generated files. Optional environment variables ALBU_MCP_ALLOWED_ROOTS, ALBU_MCP_ARTIFACT_ROOT and ALBU_MCP_MAX_PREVIEW_RUNS tune access and retention. No authentication is declared.
Before you install
The server reads local image files, so scope the allowed roots narrowly; generated previews and manifests are written to the artifact directory. It states that it does not execute arbitrary Python, fetch remote images, overwrite datasets or train models, and that a Python handoff is guarded, but review exported code before running it. Desktop only; no web execution.

Installation

In SourceWeft

  1. Open AlbumentationsX MCP in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

AlbumentationsX MCP

Model Context Protocol server for AlbumentationsX: inspect datasets, preview augmentations, refine them with visual feedback, and export reproducible pipelines.

[CI] [PyPI] [Python] [MCP Registry] [skills.sh]

[Baseline and adjusted AlbumentationsX preview contact sheets]

Ask an MCP host for several robustness variants, reject an excessive result such as too_noisy:high, compare the adjusted batch previews, and export the accepted pipeline.

Install

Claude Desktop

Download the latest albumentationsx-mcp.mcpb, install it from Settings -> Extensions -> Advanced settings, and select separate image and artifact directories.

Other MCP Hosts

Run the published server with bounded local access:

bash
uvx --from albumentationsx-mcp albumentationsx-mcp \  --allowed-root /absolute/path/to/images \  --artifact-root /absolute/path/to/albu-artifacts

run_first_preview requires the default full or dataset capability profile. The smaller review profile uses the explicit validate/render fallback in the usage guide, or you can restart with dataset or full; see configuration. Copyable host configurations are in the install guide. The repository also contains a native Codex plugin bundle. npx skills add dKosarevsky/albu-mcp installs agent guidance, not the MCP server.

First Preview

After connecting the server, ask your host:

text
Run the host smoke check. If preview_ready is true, call run_first_preview for /absolute/path/to/images with lowintensity and at most 8 images. Show me the contact sheet. When I mention a specific result, calltrace_preview_variant before adjusting it.

run_host_smoke_check returns preview_ready and a preview_request_template. If resource reads are unavailable, call get_workflow_example with example_id="client-smoke".

Try the classification robustness use case, or follow the First 10 Minutes guide. The validate_preview_request fallback, batch previews, and how to compare preview runs are in Usage. Use too_noisy:high or exposure_too_weak:medium, then optionally share one redacted loop through first-preview feedback. If setup fails, read albumentationsx://diagnostics/guide and call diagnose_environment for bounded remediation actions.

Capabilities

  • Transform discovery, schemas, recipes, and pipeline validation.
  • Classification, detection, segmentation, OCR, bbox, mask, keypoint, and dataset-quality workflows.
  • Deterministic previews, contact sheets, annotation overlays, comparison, ranking, and reports.
  • Interactive MCP Apps review with a text-only fallback for other hosts.
  • Structured feedback, tuning sessions, and Python, JSON, or YAML export.
  • Runtime-aware CPU torch.Tensor pipeline validation and guarded Python handoff.
  • MCP 2026-07-28 plus legacy negotiation; stable agent workflow resources, diagnostics, and contract snapshots.

The server does not execute arbitrary Python, fetch remote images, overwrite datasets, or train models. Reads are restricted by --allowed-root; generated files stay under --artifact-root.

Integrations

Documentation

Development

bash
uv sync --all-extras --devuv run pytestuv run ruff check .uv run ruff format --check .uv run ty check

Licensed under AGPL-3.0-or-later.

Source: README.md at commit 171e2ca

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v1.21.1LatestSep 16, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts