PDF Processor
This MCP server provides PDF processing capabilities with advanced LaTeX equation extraction, enabling AI assistants to fetch PDFs from URLs, extract text content, and recognize mathematical equations from academic papers and technical documents. Built by Michael Levinson using Python with PyMuPDF for text extraction and pix2tex for LaTeX OCR, it offers optimized performance on Apple Silicon with fallbacks for other hardware, three-step workflow (fetch, process, read) to manage memory efficiently, and both standalone MCP server and FastAPI implementations for different integration needs. The implementation includes comprehensive error handling, configurable output directories, and specialized support for academic paper processing, making it valuable for researchers analyzing mathematical papers, students working with technical documents, and any workflow requiring extraction of both text and mathematical content from PDF sources.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately. Last scanned 2026-09-19.
Scan details: Circle-IR · 2026-09-19 · Appeal
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- iot-hardware
- Source
- PulseMCP
- Repository
- github.com/michaellevinson/mcp_pdf_processor
- Author type
- human
- Last scanned
- 2026-09-19
- Updated
- 2026-09-19
Use via MCP
Resolve PDF Processor from your agent
Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.
One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp--scope user for --scope project to commit it to .mcp.json.