Docpick
Verified · yesterdaySchema-driven document extraction with local OCR + LLM. Document in, Structured JSON out.
Install
claude mcp add docpick -- uvx docpick
Our take
Local document-extraction MCP that combines OCR, schema validation, and local LLM providers to turn documents into structured JSON. The repo has a real Python package, tests, built-in schemas, and an MCP server entry point, but the registry is stale at 0.1.2 while PyPI is already 0.1.3. Expect more setup than a hosted extractor because OCR engines and local model endpoints are part of the stack.
Verification record
- yesterday
- 1
- 3 mo ago
- no
- Apache-2.0
- 2026-03-17