Docpick extracts structured JSON from documents and exposes OCR, schema discovery and extraction through a local MCP server.
Docpick extracts structured JSON from documents and exposes OCR, schema discovery and extraction through a local MCP server.
Docpick combines OCR with schema-driven extraction. Its built-in schemas cover invoices, receipts, purchase orders, bank statements and other document types. Use list_schemas to inspect the available fields before selecting a schema. Extraction returns structured data, while the OCR-only tool returns recognized text and supporting recognition information.
The Python package requires Python 3.11 or later. MCP support is an optional dependency: install docpick[mcp] before running docpick-mcp over stdio. OCR backends and the OpenAI-compatible model endpoint have their own configuration. A local model endpoint can be used, while a hosted endpoint may require its provider's credentials. Installing the MCP extra alone does not install every OCR engine.
Start with a short sample invoice whose values you can verify. Compare extracted totals, dates and line items with the source image or PDF. If a field is absent or poorly recognized, inspect the OCR text before changing the extraction prompt. Keep the source document available when reviewing a structured result, especially when totals or identifiers feed another system.
Check the linked publisher documentation and your connected client's tool list. Names and availability can vary with the server version and account permissions.
| Tool | What it does |
|---|---|
| extract_document | Extract document data using a selected schema. |
| ocr_document | Recognize document text without structured LLM extraction. |
| list_schemas | List built-in schemas and fields. |
{
"mcpServers": {
"docpick": {
"command": "docpick-mcp",
"args": []
}
}
}Python 3.11 or later, docpick[mcp], a configured OCR backend and a compatible model endpoint for structured extraction.
Generates both vector and raster images using EverArt's AI models, providing flexible storage and format conversion.
Provides file system operations, analysis, and manipulation through a standardized tool interface.
1AIVault is a local-first desktop app that acts as a portable memory vault for AI tools. It stores your memories, decisions, preferences, and reusable skills in a local SQLite database and exposes…
A Model Context Protocol server
Expose the 5dive agent-fleet CLI as Model Context Protocol tools. Point any MCP client (Claude Desktop, Cursor, Cline, or your own) at this stdio server to file tasks, inspect and message agents, and read the fleet…
Automated DOCX Redlining Engine