Ryan Malloy
c902e81e4d
Features: - 8 comprehensive PDF processing tools with intelligent fallbacks - Text extraction (PyMuPDF, pdfplumber, pypdf with auto-selection) - Table extraction (Camelot → pdfplumber → Tabula fallback chain) - OCR processing with Tesseract and preprocessing options - Document analysis (structure, metadata, scanned detection) - Image extraction with filtering capabilities - PDF to markdown conversion with metadata - Built on FastMCP framework with full MCP protocol support - Comprehensive error handling and user-friendly messages - Docker support and cross-platform compatibility - Complete test suite and examples 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <noreply@anthropic.com>
87 lines
2.0 KiB
TOML
87 lines
2.0 KiB
TOML
[project]
|
|
name = "mcp-pdf-tools"
|
|
version = "0.1.0"
|
|
description = "FastMCP server for comprehensive PDF processing - text extraction, OCR, table extraction, and more"
|
|
authors = [{name = "RPM", email = "rpm@example.com"}]
|
|
readme = "README.md"
|
|
license = {text = "MIT"}
|
|
requires-python = ">=3.10"
|
|
keywords = [
|
|
"mcp",
|
|
"fastmcp",
|
|
"pdf",
|
|
"ocr",
|
|
"text-extraction",
|
|
"table-extraction",
|
|
"pdf-processing",
|
|
"api",
|
|
"integration"
|
|
]
|
|
classifiers = [
|
|
"Development Status :: 4 - Beta",
|
|
"Intended Audience :: Developers",
|
|
"License :: OSI Approved :: MIT License",
|
|
"Programming Language :: Python :: 3",
|
|
"Programming Language :: Python :: 3.10",
|
|
"Programming Language :: Python :: 3.11",
|
|
"Programming Language :: Python :: 3.12",
|
|
"Topic :: Software Development :: Libraries :: Python Modules",
|
|
"Topic :: Text Processing :: General",
|
|
"Topic :: Office/Business",
|
|
]
|
|
dependencies = [
|
|
"fastmcp>=0.1.0",
|
|
"httpx>=0.25.0",
|
|
"pydantic>=2.0.0",
|
|
"python-dotenv>=1.0.0",
|
|
"PyMuPDF>=1.23.0",
|
|
"pdfplumber>=0.10.0",
|
|
"camelot-py[cv]>=0.11.0",
|
|
"tabula-py>=2.8.0",
|
|
"pytesseract>=0.3.10",
|
|
"pdf2image>=1.16.0",
|
|
"pypdf>=3.17.0",
|
|
"pandas>=2.0.0",
|
|
"Pillow>=10.0.0",
|
|
"markdown>=3.5.0",
|
|
]
|
|
|
|
[project.urls]
|
|
Homepage = "https://github.com/rpm/mcp-pdf-tools"
|
|
Documentation = "https://github.com/rpm/mcp-pdf-tools#readme"
|
|
Repository = "https://github.com/rpm/mcp-pdf-tools.git"
|
|
Issues = "https://github.com/rpm/mcp-pdf-tools/issues"
|
|
|
|
[project.scripts]
|
|
mcp-pdf-tools = "mcp_pdf_tools.server:main"
|
|
|
|
[project.optional-dependencies]
|
|
dev = [
|
|
"pytest>=7.0.0",
|
|
"pytest-asyncio>=0.21.0",
|
|
"black>=23.0.0",
|
|
"ruff>=0.1.0",
|
|
"mypy>=1.0.0",
|
|
"build>=0.10.0",
|
|
"twine>=4.0.0",
|
|
]
|
|
|
|
[build-system]
|
|
requires = ["hatchling"]
|
|
build-backend = "hatchling.build"
|
|
|
|
[tool.hatchling.build.targets.sdist]
|
|
include = [
|
|
"/src",
|
|
"/tests",
|
|
"/examples",
|
|
"README.md",
|
|
"LICENSE",
|
|
"MANIFEST.in",
|
|
]
|
|
|
|
[dependency-groups]
|
|
dev = [
|
|
"reportlab>=4.4.3",
|
|
]
|