PDF2MD
PDF2MD MCP server by Gavin Huang that converts PDF files to Markdown format using AI sampling capabilities through the FastMCP framework. The implementation supports both local file paths and URLs, features incremental conversion that can resume from where it left off by detecting existing page markers, and uses pymupdf4llm for PDF content extraction with fallback handling when AI sampling is unavailable. Built with comprehensive error handling for network issues, file permissions, and invalid formats, it serves developers building document processing workflows, content management systems requiring PDF-to-Markdown conversion, and AI applications that need to extract and format PDF content for further analysis or storage.
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
- ai-ml
- Source
- PulseMCP
- Repository
- github.com/gavinhuang/pdf2md-mcp
- Author type
- human
- Last scanned
- 2026-09-19
- Updated
- 2026-09-19
Use via MCP
Resolve PDF2MD 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.