Skip to content
Agentmart
Submit a tool

Docpick

Schema-driven document extraction with local OCR + LLM.

Connector by ArkNill · GitHub account verified by the MCP Registry

IndexedApache-2.0Local (stdio)★ 1
Write a review

Install

Works with Claude Code, Codex, VS Code, Cursor, Windsurf, Claude Desktop. Read the repository before you give any tool access to your data.

npx agentmarket install connector/arknill-docpick

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Schema-driven document extraction with local OCR + LLM. Document in, Structured JSON out.

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this server can do and what it asks for, from its tool list and install config. Checked Oct 25, 2026.

Tools
2 read · 1 write · 0 delete
Secrets
None asked for
Install scripts
Not scanned yet
Runs as
Python package

Tools by what they do 3

Read from the source code; the running server may list different tools.

Read 2 · Look things up without changing anything.

  • extract_document
  • list_schemas

Write 1 · Create, change, send or run things.

  • ocr_document

Files it touches

  • Any path the agent passes to its tools

Tools (3)

Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].

  • extract_document

    Extract structured data from a document using OCR + LLM. Supports PDF and image files (PNG, JPG, TIFF). Returns structured JSON matching the specified schema. Args: file_path: Path to the document file (PDF, PNG, JPG, TIFF). schema: Schema to use for extraction. Built-in: invoice, receipt, bill_of_lading, purchase_order, kr_tax_invoice, bank_statement, id_document, certificate_of_origin. ocr_engine: OCR engine to use: "auto" (default), "paddle", "easyocr", "got", "vlm". output_format: "json" (default) or "text" (OCR text only).

  • list_schemas

    List all available built-in document schemas with their fields.

  • ocr_document

    Run OCR on a document without LLM extraction. Returns recognized text as markdown with structure preserved. Args: file_path: Path to the document file (PDF, PNG, JPG, TIFF). engine: OCR engine: "auto" (default), "paddle", "easyocr", "got".

Signals

Stars
1
Forks
1
Open issues
0
Weekly downloads
285
Last commit
Apr 15, 2026 (6 months ago)
Last release
Mar 17, 2026 (7 months ago)
Last package publish
Mar 25, 2026 (7 months ago)

From GitHub (fetched Oct 24, 2026) and the package registry.

Details

Registry name
io.github.ArkNill/docpick
Version
0.1.2
Auth
No auth
Packages
pypi docpick
License
Apache-2.0
Repository
github.com/QuartzUnit/docpick
First seen
Oct 24, 2026
Last checked
Oct 25, 2026
Source
Official MCP Registrygithub-graphql

More from ArkNill

Cite this page

Docpick MCP server. Agent Mart. https://agentmart.dev/connectors/arknill-docpick (last updated 2026-10-25)