albumentationsx-mcp 1.19.0

Model Context Protocol server for AlbumentationsX augmentation previews, validation, and segmentation review.

AlbumentationsX MCP

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

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:

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

Copyable Claude Code, Cursor, Codex, and JSON 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:

Use AlbumentationsX MCP on /absolute/path/to/images.
Run the smoke check, start with a low-intensity pipeline, validate the request,
render one variant per image, and show me the contact sheet before exporting anything.

1. When the host exposes resource reads, read albumentationsx://examples/client-smoke; otherwise call run_host_smoke_check directly.
2. Continue only when preview_ready is true, then use the returned preview_request_template.
3. Call validate_preview_request before rendering and compare preview runs before accepting a candidate.
4. Give concrete feedback such as too_noisy:high or exposure_too_weak:medium, then export the final pipeline.

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.
• Stable agent workflow resources, prompts, diagnostics, and reviewed 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

• Official Albumentations MCP guide
• Official MCP Registry entry
• skills.sh agent skill
• Upstream documentation PR

Documentation

• Install and host configuration
• First 10 minutes
• Usage and recipes
• MCP Apps review and compatibility policy
• Documentation index
• CHANGELOG.md
• server.json: public MCP Registry metadata.

Development

uv sync --all-extras --dev
uv run pytest
uv run ruff check .
uv run ruff format --check .
uv run ty check

Licensed under AGPL-3.0-or-later.