Search & web / pdf-mcp
pdf-mcp
io.github.jztan/pdf-mcp · v3.5.0
Agentic RAG over one PDF or a whole folder: hybrid search, selective page reads, tables, OCR.
Description supplied by the publisher in the MCP Registry. We have not tested this server.
Install
uvx pdf-mcpPublished as an MCP bundle (.mcpb); download it from the project's GitHub releases page.
Assembled from the package metadata in the official MCP Registry (including any subcommand or flag the publisher lists). Some publishers do not list the subcommand that starts MCP mode, so confirm the command in the README, along with any required configuration and credentials, before connecting it to real data.
Signals
| GitHub stars | 150 |
| npm weekly downloads | - |
| Last push | 3d ago |
| Licence | MIT |
| Open issues | 1 |
| SECURITY.md | Yes |
| Language | Python |
| Latest version published | 2026-10-03 |
Signals captured from GitHub, npm and the official MCP Registry on October 15, 2026. See the scoring method.
Similar servers compare all →
minirag-mcp
Score 74Local-first RAG MCP server: hybrid search over a folder of your own documents
Silica Core
Score 83Retrieval over the folder the session opened: files, search, read, code_pack, write_note.
loreweave
Score 80Durable agent memory over a markdown vault: bitemporal facts, timelines, hybrid graph search.