MCP.Market

AlbumentationsX MCP server

by dKosarevsky·io.github.dKosarevsky/albu-mcp·v1.21.1·6 stars
No reviews yet

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

A88/100grade A
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
A88/100

full report

Adoption
Growing

6 stars67 downloads/wk

Reviews

Write one

Nobody has reviewed AlbumentationsX MCP yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

AlbumentationsX MCP tools (47, 5 write)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • adjust_pipeline

    Adjust a pipeline from structured preview feedback tags.

  • archive_tuning_session

    Archive an interactive tuning session without deleting its audit trail.

  • build_review_packet

    Build one host-facing first-preview handoff for one image or an image directory.

  • cleanup_preview_runswrite action

    Delete older preview runs beyond a retention count.

  • cleanup_tuning_sessionswrite action

    Delete older interactive tuning sessions, protecting active sessions by default.

  • close_tuning_session

    Close an interactive tuning session as accepted or rejected.

  • compare_preview_runs

    Compare two preview manifests to guide structured feedback and reproducible tuning.

  • delete_preview_runwrite action

    Delete one preview run and its artifacts from the configured artifact root.

  • diagnose_environment
  • explain_pipeline

    Explain likely pipeline effects, risks, and useful preview feedback tags.

  • export_pipeline

    Export a validated pipeline, optionally as a guarded CPU Tensor Python handoff.

  • export_preview_report

    Export a visual preview report with ranking, contact sheets, and decisions.

  • export_tuning_report

    Export persisted tuning decisions as markdown or JSON.

  • export_tuning_session

    Export one interactive tuning session as Markdown or JSON.

  • get_preview_manifest

    Return the manifest JSON for one recorded preview run.

  • get_transform_schema

    Get parameter schema, target support, and summary for one transform.

  • get_workflow_example

    Return an active-profile workflow example when the MCP host cannot read resources.

  • inspect_dataset_quality

    Inspect local dataset image quality before first preview rendering.

  • interpret_preview_feedback

    Convert free-form preview feedback into structured feedback tags.

  • list_feedback_tags

    List structured feedback tags accepted by adjust_pipeline.

  • list_preview_feedback

    List concrete preview feedback records.

  • list_preview_runs

    List recent preview runs recorded under the configured artifact root.

  • list_quality_profiles

    List task-aware quality profiles accepted by preview comparison tools.

  • list_tuning_decisions

    List persisted local tuning decisions.

  • list_tuning_sessions

    List persisted interactive preview tuning sessions.

  • plan_augmentation_policy

    Plan a preview-gated augmentation policy for a task and objective.

  • plan_augmentation_policy_candidates

    Plan 3-5 preview-gated augmentation policy candidates for side-by-side review.

  • plan_dataset_onboarding

    Plan the first safe preview for one local image or an image directory.

  • plan_policy_iteration

    Plan the next preview-gated policy iteration from concrete review feedback.

  • plan_preview_review

    Plan the next review action for one baseline-to-candidate preview comparison.

  • rank_preview_candidates

    Rank multiple candidate preview runs against one baseline.

  • recommend_pipeline

    Recommend a conservative starter pipeline for a CV task.

  • recommend_recipe

    Recommend a task-aware starter pipeline, quality profile, and preview workflow.

  • record_preview_feedback

    Persist user feedback for one concrete preview image variant.

  • record_tuning_decision

    Persist a local tuning decision for one preview comparison.

  • record_tuning_session_step

    Record one candidate comparison inside an interactive tuning session.

  • render_preview

    Render deterministic preview artifacts for local input images.

  • render_preview_batch

    Render deterministic batch preview artifacts and contact sheets for local input images.

  • run_first_previewwrite action

    Run one bounded, validated first preview for a local image or image directory.

  • run_host_smoke_checkwrite action

    Run a read-only host preflight; reading the client-smoke resource is optional.

  • score_dataset_preview_candidates

    Score several preview candidates as one dataset-level decision set.

  • search_transforms

    Search AlbumentationsX transform metadata.

  • start_tuning_session

    Start a persistent multi-step preview tuning session.

  • summarize_tuning_session

    Summarize a baseline-to-candidate preview tuning step.

  • trace_preview_variant

    Read the applied-transform trace for one rendered preview variant.

  • validate_pipeline

    Validate a pipeline spec and optional CPU Tensor boundary before export.

  • validate_preview_request

    Validate a preview request before rendering local preview artifacts.

Public scan report

scanner v0.1.10 · 2026-11-03 · same rubric, same numbers if you re-run it

no findings
  • Code scan127 source files scanned25/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitylocal package, no credentials required12/15
  • Maintenancelast push 82 days ago12/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
Overall 88/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How AlbumentationsX MCP compares

Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
88/100
higher than 75% of 48,255 servers
Tools
47
the typical server has 7
Tools that change things
11%
typical: 0%. Fewer write tools means less an agent can break
GitHub stars
6
more than 85% of 28,688 servers
Downloads a week
67
more than 52% of 12,191 servers with a package

What its tools let an agent do: 39 read · 3 change · 2 delete · 3 run or deploy

Install AlbumentationsX MCP in Claude Code, Cursor or VS Code

claude mcp add albu-mcp -- uvx albumentationsx-mcp
Add to Cursor

What the publisher says

From the AlbumentationsX MCP repository's README, as published. We do not edit it. Read it on GitHub

AlbumentationsX MCP

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

<!-- mcp-name: io.github.dKosarevsky/albu-mcp -->

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

runfirstpreview 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:

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

runhostsmokecheck returns previewready and a previewrequesttemplate. If resource reads are unavailable, call getworkflowexample with example_id="client-smoke".

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

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

AlbumentationsX MCP: common questions

Is AlbumentationsX MCP server safe?
Yes, by our scan: it is graded A (88/100). Read the AlbumentationsX MCP safety report
How do I install AlbumentationsX MCP?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does AlbumentationsX MCP need an API key?
No secret keys are declared. It reads 3 settings from the environment.
Is AlbumentationsX MCP maintained?
The last commit was 82 days ago (2026-08-14). The latest release is v1.21.1.
How does AlbumentationsX MCP compare with other MCP servers?
safety score 88/100 (higher than 75% of 48,255 servers); tools 47 (the typical server has 7); tools that change things 11% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.