PaddleOCR
Rank #34,353pulsemcp/paddlepaddle-paddleocr
Integrates with PaddleOCR and PP-StructureV3 to extract text from images and PDFs with confidence scores and bounding boxes, plus parse complex documents into structured markdown with embedded images, tables, and formulas.
PaddleOCR is a Model Context Protocol (MCP) server published by PaddlePaddle. It ranks #34,353 of 76,851 servers tracked on MCP Toplist. PaddleOCR is listed on PulseMCP, and ships as a single rolling release with no explicit version metadata. It was first listed on Jul 16, 2025.
Ranks ahead of 42,498 of 76,851 servers on MCP Toplist.
Listed on 1 registry
PaddlePaddle
Not versioned
This server is published through a registry that does not expose explicit version metadata, and no GitHub release tags were found on the linked repository. The listing tracks a single rolling release.
Frequently asked questions
- Who maintains PaddleOCR?
- PaddleOCR is maintained by PaddlePaddle, which publishes 2 MCP servers (6 total versions) tracked on MCP Toplist.
- Is PaddleOCR listed on the Official MCP Registry?
- PaddleOCR is not on the Official MCP Registry. It is listed on PulseMCP.
- How many versions does PaddleOCR have?
- PaddleOCR ships as a single rolling release with no explicit version metadata.
- Where can I find the source code for PaddleOCR?
- The source code for PaddleOCR is hosted at github.com/paddlepaddle/paddleocr/tree/HEAD/mcp_server.