pixlint 1.0__tar.gz

pixlint-1.0/LICENSE

@@ -0,0 +1,116 @@
+Copyright © 2026 AMIT SINGH RAJAWAT
+
+PixLint is licensed under the PolyForm Strict License 1.0.0.
+
+Plain-language summary (not a substitute for the license below): you may use
+this software for permitted (noncommercial) purposes only. You may NOT
+distribute the software, and you may NOT make changes or new works based on it.
+For any other use — including commercial use, redistribution, or modification —
+you must obtain a separate written license from the copyright holder.
+
+--------------------------------------------------------------------------------
+
+# PolyForm Strict License 1.0.0
+
+<https://polyformproject.org/licenses/strict/1.0.0>
+
+## Acceptance
+
+In order to get any license under these terms, you must agree
+to them as both strict obligations and conditions to all
+your licenses.
+
+## Copyright License
+
+The licensor grants you a copyright license for the software
+to do everything you might do with the software that would
+otherwise infringe the licensor's copyright in it for any
+permitted purpose, other than distributing the software or
+making changes or new works based on the software.
+
+## Patent License
+
+The licensor grants you a patent license for the software that
+covers patent claims the licensor can license, or becomes able
+to license, that you would infringe by using the software.
+
+## Noncommercial Purposes
+
+Any noncommercial purpose is a permitted purpose.
+
+## Personal Uses
+
+Personal use for research, experiment, and testing for
+the benefit of public knowledge, personal study, private
+entertainment, hobby projects, amateur pursuits, or religious
+observance, without any anticipated commercial application,
+is use for a permitted purpose.
+
+## Noncommercial Organizations
+
+Use by any charitable organization, educational institution,
+public research organization, public safety or health
+organization, environmental protection organization,
+or government institution is use for a permitted purpose
+regardless of the source of funding or obligations resulting
+from the funding.
+
+## Fair Use
+
+You may have "fair use" rights for the software under the
+law. These terms do not limit them.
+
+## No Other Rights
+
+These terms do not allow you to sublicense or transfer any of
+your licenses to anyone else, or prevent the licensor from
+granting licenses to anyone else.  These terms do not imply
+any other licenses.
+
+## Patent Defense
+
+If you make any written claim that the software infringes or
+contributes to infringement of any patent, your patent license
+for the software granted under these terms ends immediately. If
+your company makes such a claim, your patent license ends
+immediately for work on behalf of your company.
+
+## Violations
+
+The first time you are notified in writing that you have
+violated any of these terms, or done anything with the software
+not covered by your licenses, your licenses can nonetheless
+continue if you come into full compliance with these terms,
+and take practical steps to correct past violations, within
+32 days of receiving notice.  Otherwise, all your licenses
+end immediately.
+
+## No Liability
+
+***As far as the law allows, the software comes as is, without
+any warranty or condition, and the licensor will not be liable
+to you for any damages arising out of these terms or the use
+or nature of the software, under any kind of legal claim.***
+
+## Definitions
+
+The **licensor** is the individual or entity offering these
+terms, and the **software** is the software the licensor makes
+available under these terms.
+
+**You** refers to the individual or entity agreeing to these
+terms.
+
+**Your company** is any legal entity, sole proprietorship,
+or other kind of organization that you work for, plus all
+organizations that have control over, are under the control of,
+or are under common control with that organization.  **Control**
+means ownership of substantially all the assets of an entity,
+or the power to direct its management and policies by vote,
+contract, or otherwise.  Control can be direct or indirect.
+
+**Your licenses** are all the licenses granted to you for the
+software under these terms.
+
+**Use** means anything you do with the software requiring one
+of your licenses.

pixlint-1.0/MANIFEST.in

@@ -0,0 +1,26 @@
+# Files to INCLUDE in the source distribution (sdist)
+include README.md
+include LICENSE
+include requirements.txt
+include pyproject.toml
+recursive-include src/pixlint *.py
+
+# Files/dirs to EXCLUDE from the source distribution
+exclude plan.md
+exclude test_client.py
+exclude uv.lock
+exclude bandit*.json
+exclude .coverage
+exclude Dockerfile
+exclude .dockerignore
+prune tests
+prune test_runner
+prune docs
+prune examples
+prune build
+prune dist
+prune .github
+global-exclude *.pyc
+global-exclude __pycache__
+global-exclude *.so
+global-exclude .DS_Store

pixlint-1.0/PKG-INFO

@@ -0,0 +1,199 @@
+Metadata-Version: 2.4
+Name: pixlint
+Version: 1.0
+Summary: MCP server for managing, analyzing, and optimizing computer vision datasets
+Author: PixLint Contributors
+License: PolyForm Strict License 1.0.0
+Project-URL: Homepage, https://github.com/amitsingh-24/PixLint
+Project-URL: Repository, https://github.com/amitsingh-24/PixLint
+Project-URL: Issues, https://github.com/amitsingh-24/PixLint/issues
+Keywords: computer-vision,datasets,mcp,model-context-protocol,augmentation
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
+Classifier: Intended Audience :: Science/Research
+Classifier: License :: Other/Proprietary License
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Classifier: Topic :: Scientific/Engineering :: Image Processing
+Classifier: Topic :: Software Development :: Libraries :: Python Modules
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: mcp>=1.0.0
+Requires-Dist: pydantic>=2.0
+Requires-Dist: Pillow>=10.0
+Requires-Dist: opencv-python-headless>=4.8
+Requires-Dist: numpy>=1.24
+Requires-Dist: scipy>=1.11
+Requires-Dist: defusedxml>=0.7
+Requires-Dist: PyYAML>=6.0
+Requires-Dist: imagehash>=4.3
+Requires-Dist: scikit-image>=0.21
+Requires-Dist: scikit-learn>=1.3
+Requires-Dist: pandas>=2.0
+Requires-Dist: albumentations>=1.3
+Requires-Dist: matplotlib>=3.7
+Requires-Dist: rich>=13.0
+Requires-Dist: tqdm>=4.65
+Provides-Extra: dev
+Requires-Dist: pytest>=7.4; extra == "dev"
+Requires-Dist: pytest-cov>=4.1; extra == "dev"
+Requires-Dist: pytest-asyncio>=0.21; extra == "dev"
+Requires-Dist: ruff>=0.1; extra == "dev"
+Requires-Dist: mypy>=1.6; extra == "dev"
+Provides-Extra: torch
+Requires-Dist: torch>=2.0; extra == "torch"
+Requires-Dist: torchvision>=0.15; extra == "torch"
+Provides-Extra: tensorflow
+Requires-Dist: tensorflow>=2.12; extra == "tensorflow"
+Provides-Extra: clip
+Requires-Dist: clip-anytorch>=2.5; extra == "clip"
+Provides-Extra: umap
+Requires-Dist: umap-learn>=0.5; extra == "umap"
+Provides-Extra: hdf5
+Requires-Dist: h5py>=3.8; extra == "hdf5"
+Provides-Extra: huggingface
+Requires-Dist: datasets>=2.14; extra == "huggingface"
+Requires-Dist: huggingface-hub>=0.19; extra == "huggingface"
+Provides-Extra: dashboard
+Requires-Dist: streamlit>=1.28; extra == "dashboard"
+Provides-Extra: all
+Requires-Dist: pixlint[clip,dashboard,dev,hdf5,huggingface,tensorflow,torch,umap]; extra == "all"
+Dynamic: license-file
+
+# PixLint
+
+**Lint, curate, and prepare computer-vision datasets — right from your AI assistant.**
+
+[![Python](https://img.shields.io/badge/python-3.10%2B-blue.svg)](https://python.org)
+[![License](https://img.shields.io/badge/license-PolyForm%20Strict%201.0.0-orange.svg)](LICENSE)
+[![MCP](https://img.shields.io/badge/MCP-server-purple.svg)](https://modelcontextprotocol.io)
+
+PixLint is an [MCP](https://modelcontextprotocol.io) server that gives AI assistants — Claude, Cursor, VS Code, and any MCP client — direct, conversational access to a complete computer-vision dataset toolkit: analyze quality, find duplicates and label errors, clean and curate, split, augment, convert formats, and export to every major training framework.
+
+It runs locally over stdio, or self-hosted on the internet over authenticated HTTP.
+
+---
+
+## Why PixLint
+
+Most dataset tooling is either a paid SaaS or a heavy GUI app. PixLint is a single, open-source, self-hostable server an AI agent can drive end to end — and it does things others keep behind paid tiers:
+
+- **🩺 Dataset Doctor** — one call runs a full diagnostic and returns a prioritized, *executable* fix plan.
+- **Label-error detection** — automatically surface images that are probably mislabeled.
+- **Natural-language query** — *"find blurry images with a person on the left"*, answered over your data.
+- **Weak-slice discovery** — find under-represented or low-quality slices to collect or augment next.
+- **Curation that writes a new dataset** — clean / filter / remap, not just report.
+- **Auto-labeling** with a pretrained detector, and **one-command Hugging Face publishing**.
+
+---
+
+## Features
+
+**103 operations** — 67 tools, 23 resources, 13 prompts.
+
+| Category | What you get |
+|----------|--------------|
+| **Load** | COCO · VOC · YOLO · KITTI · folder, plus cloud (S3 / GCS / Azure) |
+| **Analyze** | Duplicates · quality (blur/exposure/noise/contrast) · integrity · class distribution · embeddings · semantic search · outliers · health score |
+| **Data intelligence** | Dataset Doctor readiness report · label-error detection · natural-language query · weak-slice / bias discovery |
+| **Curate** | Filter to a subset · clean (corrupt / out-of-bounds / degenerate / duplicates) · remap classes — each produces a new dataset |
+| **Augment & transform** | YOLO/classification/segmentation pipelines · resize · normalize · format conversion |
+| **Split** | Stratified / random / temporal / grouped · k-fold · data-leakage detection |
+| **Auto-label** | Pretrained COCO-80 detector → pre-annotated dataset |
+| **Export & publish** | PyTorch · TensorFlow · Ultralytics · HDF5 · WebDataset · FiftyOne · CVAT · LabelMe · Hugging Face Hub |
+| **Pipelines** | Compose multi-step workflows and reuse pre-built templates |
+
+---
+
+## Quick Start
+
+### 1. Install
+
+```bash
+pip install pixlint
+```
+
+Optional extras add heavier capabilities:
+
+```bash
+pip install "pixlint[torch]"        # embeddings, auto-labeling, label-error detection
+pip install "pixlint[huggingface]"  # Hugging Face export + publishing
+pip install "pixlint[all]"          # everything
+```
+
+### 2. Connect your AI assistant
+
+**Claude Desktop** — `claude_desktop_config.json`:
+
+```json
+{
+  "mcpServers": {
+    "pixlint": {
+      "command": "pixlint",
+      "env": { "CV_DATA_DIR": "/path/to/your/datasets" }
+    }
+  }
+}
+```
+
+**Cursor / VS Code** — `.cursor/mcp.json` or `.vscode/mcp.json`:
+
+```json
+{
+  "mcpServers": {
+    "pixlint": {
+      "command": "pixlint",
+      "env": { "CV_DATA_DIR": "/path/to/your/datasets" }
+    }
+  }
+}
+```
+
+`CV_DATA_DIR` is the directory PixLint is allowed to read datasets from.
+
+### 3. Just ask
+
+> *"Load my dataset at `/data/coco_person`, give it a readiness report, then clean it and export for YOLO."*
+
+Your assistant calls the right PixLint tools in sequence — diagnose, clean, split, export — and hands back a training-ready dataset.
+
+---
+
+## Security
+
+PixLint touches the filesystem and can be exposed to a network, so protections run on **every** tool call:
+
+- Paths are confined to your configured data directory (reads **and** writes).
+- Credentials come only from environment variables, never tool inputs.
+- Per-call rate limiting, concurrency limits, and audit logging.
+- Decompression-bomb protection on image decode.
+- Optional bearer-token authentication for the HTTP transport.
+
+See the [Security Guide](docs/security.md) for the full threat model and the recommended production checklist.
+
+---
+
+## Documentation
+
+| Guide | Description |
+|-------|-------------|
+| [Getting Started](docs/getting_started.md) | Installation, configuration, first steps |
+| [MCP Client Setup](docs/mcp_client_setup.md) | Claude, Cursor, VS Code, and remote/HTTP hosting |
+| [API Reference](docs/api_reference.md) | All 67 tools with parameters |
+| [Security Guide](docs/security.md) | Threat model, configuration, hosting |
+| [Pipeline Templates](docs/pipeline_templates.md) | Pre-built and custom pipelines |
+
+Runnable scripts live in [`examples/`](examples/).
+
+---
+
+## License
+
+PixLint is source-available under the **PolyForm Strict License 1.0.0** — see [LICENSE](LICENSE).
+You may use it for permitted (noncommercial) purposes; commercial use, redistribution, or
+modification requires a separate license from the copyright holder. Contributions are welcome
+via pull request.

pixlint-1.0/README.md

@@ -0,0 +1,133 @@
+# PixLint
+
+**Lint, curate, and prepare computer-vision datasets — right from your AI assistant.**
+
+[![Python](https://img.shields.io/badge/python-3.10%2B-blue.svg)](https://python.org)
+[![License](https://img.shields.io/badge/license-PolyForm%20Strict%201.0.0-orange.svg)](LICENSE)
+[![MCP](https://img.shields.io/badge/MCP-server-purple.svg)](https://modelcontextprotocol.io)
+
+PixLint is an [MCP](https://modelcontextprotocol.io) server that gives AI assistants — Claude, Cursor, VS Code, and any MCP client — direct, conversational access to a complete computer-vision dataset toolkit: analyze quality, find duplicates and label errors, clean and curate, split, augment, convert formats, and export to every major training framework.
+
+It runs locally over stdio, or self-hosted on the internet over authenticated HTTP.
+
+---
+
+## Why PixLint
+
+Most dataset tooling is either a paid SaaS or a heavy GUI app. PixLint is a single, open-source, self-hostable server an AI agent can drive end to end — and it does things others keep behind paid tiers:
+
+- **🩺 Dataset Doctor** — one call runs a full diagnostic and returns a prioritized, *executable* fix plan.
+- **Label-error detection** — automatically surface images that are probably mislabeled.
+- **Natural-language query** — *"find blurry images with a person on the left"*, answered over your data.
+- **Weak-slice discovery** — find under-represented or low-quality slices to collect or augment next.
+- **Curation that writes a new dataset** — clean / filter / remap, not just report.
+- **Auto-labeling** with a pretrained detector, and **one-command Hugging Face publishing**.
+
+---
+
+## Features
+
+**103 operations** — 67 tools, 23 resources, 13 prompts.
+
+| Category | What you get |
+|----------|--------------|
+| **Load** | COCO · VOC · YOLO · KITTI · folder, plus cloud (S3 / GCS / Azure) |
+| **Analyze** | Duplicates · quality (blur/exposure/noise/contrast) · integrity · class distribution · embeddings · semantic search · outliers · health score |
+| **Data intelligence** | Dataset Doctor readiness report · label-error detection · natural-language query · weak-slice / bias discovery |
+| **Curate** | Filter to a subset · clean (corrupt / out-of-bounds / degenerate / duplicates) · remap classes — each produces a new dataset |
+| **Augment & transform** | YOLO/classification/segmentation pipelines · resize · normalize · format conversion |
+| **Split** | Stratified / random / temporal / grouped · k-fold · data-leakage detection |
+| **Auto-label** | Pretrained COCO-80 detector → pre-annotated dataset |
+| **Export & publish** | PyTorch · TensorFlow · Ultralytics · HDF5 · WebDataset · FiftyOne · CVAT · LabelMe · Hugging Face Hub |
+| **Pipelines** | Compose multi-step workflows and reuse pre-built templates |
+
+---
+
+## Quick Start
+
+### 1. Install
+
+```bash
+pip install pixlint
+```
+
+Optional extras add heavier capabilities:
+
+```bash
+pip install "pixlint[torch]"        # embeddings, auto-labeling, label-error detection
+pip install "pixlint[huggingface]"  # Hugging Face export + publishing
+pip install "pixlint[all]"          # everything
+```
+
+### 2. Connect your AI assistant
+
+**Claude Desktop** — `claude_desktop_config.json`:
+
+```json
+{
+  "mcpServers": {
+    "pixlint": {
+      "command": "pixlint",
+      "env": { "CV_DATA_DIR": "/path/to/your/datasets" }
+    }
+  }
+}
+```
+
+**Cursor / VS Code** — `.cursor/mcp.json` or `.vscode/mcp.json`:
+
+```json
+{
+  "mcpServers": {
+    "pixlint": {
+      "command": "pixlint",
+      "env": { "CV_DATA_DIR": "/path/to/your/datasets" }
+    }
+  }
+}
+```
+
+`CV_DATA_DIR` is the directory PixLint is allowed to read datasets from.
+
+### 3. Just ask
+
+> *"Load my dataset at `/data/coco_person`, give it a readiness report, then clean it and export for YOLO."*
+
+Your assistant calls the right PixLint tools in sequence — diagnose, clean, split, export — and hands back a training-ready dataset.
+
+---
+
+## Security
+
+PixLint touches the filesystem and can be exposed to a network, so protections run on **every** tool call:
+
+- Paths are confined to your configured data directory (reads **and** writes).
+- Credentials come only from environment variables, never tool inputs.
+- Per-call rate limiting, concurrency limits, and audit logging.
+- Decompression-bomb protection on image decode.
+- Optional bearer-token authentication for the HTTP transport.
+
+See the [Security Guide](docs/security.md) for the full threat model and the recommended production checklist.
+
+---
+
+## Documentation
+
+| Guide | Description |
+|-------|-------------|
+| [Getting Started](docs/getting_started.md) | Installation, configuration, first steps |
+| [MCP Client Setup](docs/mcp_client_setup.md) | Claude, Cursor, VS Code, and remote/HTTP hosting |
+| [API Reference](docs/api_reference.md) | All 67 tools with parameters |
+| [Security Guide](docs/security.md) | Threat model, configuration, hosting |
+| [Pipeline Templates](docs/pipeline_templates.md) | Pre-built and custom pipelines |
+
+Runnable scripts live in [`examples/`](examples/).
+
+---
+
+## License
+
+PixLint is source-available under the **PolyForm Strict License 1.0.0** — see [LICENSE](LICENSE).
+You may use it for permitted (noncommercial) purposes; commercial use, redistribution, or
+modification requires a separate license from the copyright holder. Contributions are welcome
+via pull request.

pixlint-1.0/pyproject.toml

@@ -0,0 +1,113 @@
+[project]
+name = "pixlint"
+version = "1.0"
+description = "MCP server for managing, analyzing, and optimizing computer vision datasets"
+readme = "README.md"
+requires-python = ">=3.10"
+license = {text = "PolyForm Strict License 1.0.0"}
+authors = [
+    {name = "PixLint Contributors"},
+]
+keywords = ["computer-vision", "datasets", "mcp", "model-context-protocol", "augmentation"]
+classifiers = [
+    "Development Status :: 4 - Beta",
+    "Intended Audience :: Developers",
+    "Intended Audience :: Science/Research",
+    "License :: Other/Proprietary License",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3.10",
+    "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3.12",
+    "Topic :: Scientific/Engineering :: Artificial Intelligence",
+    "Topic :: Scientific/Engineering :: Image Processing",
+    "Topic :: Software Development :: Libraries :: Python Modules",
+]
+dependencies = [
+    "mcp>=1.0.0",
+    "pydantic>=2.0",
+    "Pillow>=10.0",
+    "opencv-python-headless>=4.8",
+    "numpy>=1.24",
+    "scipy>=1.11",
+    "defusedxml>=0.7",
+    "PyYAML>=6.0",
+    "imagehash>=4.3",
+    "scikit-image>=0.21",
+    "scikit-learn>=1.3",
+    "pandas>=2.0",
+    "albumentations>=1.3",
+    "matplotlib>=3.7",
+    "rich>=13.0",
+    "tqdm>=4.65",
+]
+
+[project.optional-dependencies]
+dev = [
+    "pytest>=7.4",
+    "pytest-cov>=4.1",
+    "pytest-asyncio>=0.21",
+    "ruff>=0.1",
+    "mypy>=1.6",
+]
+torch = [
+    "torch>=2.0",
+    "torchvision>=0.15",
+]
+tensorflow = [
+    "tensorflow>=2.12",
+]
+clip = [
+    # PyPI-published repackaging of OpenAI CLIP (installs as `import clip`).
+    # A direct git URL is not allowed by PyPI, so we use this instead.
+    "clip-anytorch>=2.5",
+]
+umap = [
+    "umap-learn>=0.5",
+]
+hdf5 = [
+    "h5py>=3.8",
+]
+huggingface = [
+    "datasets>=2.14",
+    "huggingface-hub>=0.19",
+]
+dashboard = [
+    "streamlit>=1.28",
+]
+all = [
+    "pixlint[dev,torch,tensorflow,clip,umap,hdf5,huggingface,dashboard]",
+]
+
+[project.urls]
+Homepage = "https://github.com/amitsingh-24/PixLint"
+Repository = "https://github.com/amitsingh-24/PixLint"
+Issues = "https://github.com/amitsingh-24/PixLint/issues"
+
+[project.scripts]
+pixlint = "pixlint.server:main"
+
+[build-system]
+requires = ["setuptools>=68.0"]
+build-backend = "setuptools.build_meta"
+
+[tool.setuptools.packages.find]
+where = ["src"]
+
+[tool.ruff]
+line-length = 100
+target-version = "py310"
+
+[tool.pytest.ini_options]
+testpaths = ["tests"]
+python_files = ["test_*.py"]
+
+[tool.coverage.run]
+source = ["pixlint"]
+omit = ["*/tests/*"]
+
+[tool.coverage.report]
+exclude_lines = [
+    "pragma: no cover",
+    "def __repr__",
+    "if __name__ == .__main__.:",
+]

pixlint-1.0/requirements.txt

@@ -0,0 +1,57 @@
+# Core
+mcp>=1.0.0
+pydantic>=2.0
+Pillow>=10.0
+opencv-python-headless>=4.8
+numpy>=1.24
+scipy>=1.11
+defusedxml>=0.7
+PyYAML>=6.0
+imagehash>=4.3
+scikit-image>=0.21
+scikit-learn>=1.3
+pandas>=2.0
+albumentations>=1.3
+matplotlib>=3.7
+rich>=13.0
+tqdm>=4.65
+
+# Development
+pytest>=7.4
+pytest-cov>=4.1
+pytest-asyncio>=0.21
+ruff>=0.1
+mypy>=1.6
+
+# Optional: Torch-based features
+torch>=2.0
+torchvision>=0.15
+
+# Optional: CLIP for semantic search
+# clip @ git+https://github.com/openai/CLIP.git
+
+# Optional: TensorFlow export
+# tensorflow>=2.12
+
+# Optional: UMAP visualization
+# umap-learn>=0.5
+
+# Optional: HDF5 export
+# h5py>=3.8
+
+# Optional: Cloud storage
+# boto3>=1.28        # S3
+# google-cloud-storage>=2.10  # GCS
+# azure-storage-blob>=12.19   # Azure
+
+# Optional: BLIP captioning
+# transformers>=4.35
+
+# Optional: Dashboard
+# streamlit>=1.28
+
+# Optional: WebDataset export
+# webdataset>=0.2
+
+# Optional: FiftyOne export
+# fiftyone>=0.20

pixlint-1.0/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+