Initial commit

Author: Rajan Shukla

.github/workflows/publish.yml

@@ -0,0 +1 @@
+ 

.gitignore

@@ -0,0 +1,38 @@
+# Python
+__pycache__/
+*.py[cod]
+*$py.class
+*.so
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+
+# Virtual Environment
+.env
+.venv
+env/
+venv/
+ENV/
+
+# IDE
+.idea/
+.vscode/
+*.swp
+*.swo
+
+# OS
+.DS_Store
+Thumbs.db

.python-version

@@ -0,0 +1 @@
+3.11

LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2024 Rajan Shukla
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE. 

README.md

@@ -0,0 +1,109 @@
+# MCP OCR Server
+
+A production-grade OCR server built using MCP (Model Context Protocol) that provides OCR capabilities through a simple interface.
+
+## Features
+
+- Extract text from images using Tesseract OCR
+- Support for multiple input types:
+  - Local image files
+  - Image URLs
+  - Raw image bytes
+- Automatic Tesseract installation
+- Support for multiple languages
+- Production-ready error handling
+
+## Installation
+
+```bash
+# Using pip
+pip install mcp-ocr
+
+# Using uv
+uv pip install mcp-ocr
+```
+
+Tesseract will be installed automatically on supported platforms:
+- macOS (via Homebrew)
+- Linux (via apt, dnf, or pacman)
+- Windows (manual installation instructions provided)
+
+## Usage
+
+### As an MCP Server
+
+1. Start the server:
+```bash
+python -m mcp_ocr
+```
+
+2. Configure Claude for Desktop:
+Add to `~/Library/Application Support/Claude/claude_desktop_config.json`:
+```json
+{
+    "mcpServers": {
+        "ocr": {
+            "command": "python",
+            "args": ["-m", "mcp_ocr"]
+        }
+    }
+}
+```
+
+### Available Tools
+
+#### perform_ocr
+Extract text from images:
+```python
+# From file
+perform_ocr("/path/to/image.jpg")
+
+# From URL
+perform_ocr("https://example.com/image.jpg")
+
+# From bytes
+perform_ocr(image_bytes)
+```
+
+#### get_supported_languages
+List available OCR languages:
+```python
+get_supported_languages()
+```
+
+## Development
+
+1. Clone the repository:
+```bash
+git clone https://github.com/yourusername/mcp-ocr.git
+cd mcp-ocr
+```
+
+2. Set up development environment:
+```bash
+uv venv
+source .venv/bin/activate  # On Windows: .venv\Scripts\activate
+uv pip install -e .
+```
+
+3. Run tests:
+```bash
+pytest
+```
+
+## Contributing
+
+1. Fork the repository
+2. Create your feature branch (`git checkout -b feature/amazing-feature`)
+3. Commit your changes (`git commit -m 'Add amazing feature'`)
+4. Push to the branch (`git push origin feature/amazing-feature`)
+5. Open a Pull Request
+
+## License
+
+This project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.
+
+## Acknowledgments
+
+- [Tesseract OCR](https://github.com/tesseract-ocr/tesseract)
+- [Model Context Protocol](https://modelcontextprotocol.io)

hello.py

@@ -0,0 +1,6 @@
+def main():
+    print("Hello from mcp-ocr!")
+
+
+if __name__ == "__main__":
+    main()

pyproject.toml

@@ -0,0 +1,49 @@
+[project]
+name = "mcp-ocr"
+version = "0.1.0"
+description = "MCP server for OCR functionality using Tesseract"
+readme = "README.md"
+requires-python = ">=3.11"
+dependencies = [
+    "mcp[cli]>=1.2.0",
+    "pytesseract>=0.3.10",
+    "opencv-python>=4.8.0",
+    "numpy>=1.24.0",
+    "pillow>=10.0.0",
+    "httpx>=0.24.0"
+]
+authors = [
+    { name = "Rajan Shukla", email = "[email protected]" }
+]
+license = { text = "MIT" }
+classifiers = [
+    "Development Status :: 4 - Beta",
+    "Intended Audience :: Developers",
+    "License :: OSI Approved :: MIT License",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3.11",
+    "Topic :: Software Development :: Libraries :: Python Modules",
+    "Operating System :: OS Independent",
+    "Environment :: Console",
+]
+
+[project.scripts]
+mcp-ocr = "mcp_ocr.__main__:main"
+
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"
+
+[tool.hatch.build.targets.wheel]
+packages = ["src/mcp_ocr"]
+
+[tool.hatch.build.hooks.custom]
+dependencies = ["hatch-requirements-txt"]
+
+[project.urls]
+Homepage = "https://github.com/yourusername/mcp-ocr"
+Documentation = "https://github.com/yourusername/mcp-ocr#readme"
+Issues = "https://github.com/yourusername/mcp-ocr/issues"
+
+[tool.hatch.metadata]
+allow-direct-references = true

src/mcp_ocr/__init__.py

@@ -0,0 +1,7 @@
+"""MCP OCR: A production-grade OCR server built using MCP (Model Context Protocol)."""
+
+__version__ = "0.1.0"
+
+from .server import mcp, perform_ocr, get_supported_languages
+
+__all__ = ["mcp", "perform_ocr", "get_supported_languages"]

src/mcp_ocr/__main__.py

@@ -0,0 +1,18 @@
+#!/usr/bin/env python3
+"""
+Command-line entry point for the MCP OCR Server.
+"""
+
+import argparse
+from .server import mcp
+
+def main():
+    """MCP OCR: Extract text from images using OCR."""
+    parser = argparse.ArgumentParser(
+        description="Extract text from images using OCR with support for local files, URLs, and image data."
+    )
+    parser.parse_args()
+    mcp.run()
+
+if __name__ == "__main__":
+    main()

src/mcp_ocr/install_tesseract.py

@@ -0,0 +1,67 @@
+"""Handle Tesseract installation during package setup."""
+
+import os
+import platform
+import subprocess
+import sys
+from typing import Optional
+
+def get_package_manager() -> Optional[str]:
+    """Detect the system's package manager."""
+    system = platform.system().lower()
+    
+    if system == "darwin":
+        # Check if Homebrew is installed
+        if subprocess.run(["which", "brew"], capture_output=True).returncode == 0:
+            return "brew"
+    elif system == "linux":
+        # Check for apt (Debian/Ubuntu)
+        if os.path.exists("/usr/bin/apt"):
+            return "apt"
+        # Check for dnf (Fedora)
+        elif os.path.exists("/usr/bin/dnf"):
+            return "dnf"
+        # Check for pacman (Arch)
+        elif os.path.exists("/usr/bin/pacman"):
+            return "pacman"
+    
+    return None
+
+def install_tesseract():
+    """Install Tesseract OCR based on the operating system."""
+    system = platform.system().lower()
+    pkg_manager = get_package_manager()
+    
+    try:
+        if system == "darwin" and pkg_manager == "brew":
+            subprocess.run(["brew", "install", "tesseract"], check=True)
+            
+        elif system == "linux":
+            if pkg_manager == "apt":
+                subprocess.run(["sudo", "apt-get", "update"], check=True)
+                subprocess.run(["sudo", "apt-get", "install", "-y", "tesseract-ocr"], check=True)
+            elif pkg_manager == "dnf":
+                subprocess.run(["sudo", "dnf", "install", "-y", "tesseract"], check=True)
+            elif pkg_manager == "pacman":
+                subprocess.run(["sudo", "pacman", "-S", "--noconfirm", "tesseract"], check=True)
+                
+        elif system == "windows":
+            print("For Windows users:")
+            print("Please download and install Tesseract from: https://github.com/UB-Mannheim/tesseract/wiki")
+            print("After installation, ensure the Tesseract installation directory is in your system PATH.")
+            return
+            
+        print("Tesseract OCR installed successfully!")
+        
+    except subprocess.CalledProcessError as e:
+        print(f"Error installing Tesseract: {str(e)}", file=sys.stderr)
+        print("Please install Tesseract manually:", file=sys.stderr)
+        print("- macOS: brew install tesseract", file=sys.stderr)
+        print("- Ubuntu/Debian: sudo apt-get install tesseract-ocr", file=sys.stderr)
+        print("- Fedora: sudo dnf install tesseract", file=sys.stderr)
+        print("- Arch: sudo pacman -S tesseract", file=sys.stderr)
+        print("- Windows: https://github.com/UB-Mannheim/tesseract/wiki", file=sys.stderr)
+        sys.exit(1)
+
+if __name__ == "__main__":
+    install_tesseract()