Productivity · Local MCP server
Docpick
Schema-driven document extraction with local OCR + LLM. Document in, Structured JSON out.
What the MCP Registry states
The entry as published to the official MCP Registry (read 2026-10-04), latest version.
- Registry name
io.github.ArkNill/docpick- Version
- 0.1.2
- Status
- Active
- Category
- productivity
- Transport
- stdio (local process)
- Package
- PyPI
- Published
- 2026-03-17
- Updated
- 2026-03-17
- Publisher
- ArkNill (GitHub) · 7 servers with pages here
- Repository
- github.com/QuartzUnit/docpick
- Source
- Registry API entry
Packages
| Registry | Package | Version | Transport |
|---|---|---|---|
| PyPI | docpick | 0.1.2 | stdio |
How to connect Docpick
Docpick runs locally from a Python package published to PyPI: docpick version 0.1.2. It speaks MCP over stdio, so the client starts it as a program and talks to it through standard input and output. It needs Python; clients usually start it with uvx (from uv) or after pip install — the usual command is uvx docpick.
In the mcpServers JSON format that many desktop and editor MCP clients read, the entry looks like this (placeholders in angle brackets):
{
"mcpServers": {
"docpick": {
"command": "uvx",
"args": [
"docpick"
]
}
}
}Derived from the registry entry, not tested here. What the server does, and on what terms, is set by its publisher; check its repository or website before giving it access to your accounts or files. How to add an MCP server to an assistant · Before you connect
More from ArkNill (GitHub)
| Server | Runs |
|---|---|
| BrowsegrabToken-efficient browser agent for local LLMs. Playwright + accessibility tree + MarkGrab. | Local · stdio |
| DiffgrabWeb page change tracking with structured diffs. markgrab + snapgrab integration. | Local · stdio |
| EmbgrepLocal semantic search — embedding-powered grep for files, zero external services. | Local · stdio |
| FeedKitRSS/Atom feed collection with 417 curated feeds. Python MCP server. | Local · stdio |
| MarkGrabUniversal web content extraction — any URL to LLM-ready markdown. HTML, YouTube, PDF, DOCX. | Local · stdio |
| SnapgrabURL to screenshot with metadata. Python MCP server. Claude Vision optimized. | Local · stdio |
More productivity servers
| Server | Runs |
|---|---|
| Docket NexusSearch public U.S. federal litigation: companies, cases, dockets and document metadata. | Remote · HTTP |
| Docling MCPConvert PDFs and other documents to structured formats via Docling, for AI applications. | Local · stdio |
| DocMakeGenerate DOCX and PDF documents from your DocMake templates. | Local · stdio |
| docmill.ioGenerate PDF, DOCX, and XLSX documents from JSON data and create reusable templates via Docmill. | Local · stdio |
| DocQA MCPAI document verification: catch hallucinations, arithmetic errors, and field mismatches. | Local · stdio |
| DocraptorTurn HTML or a live URL into polished PDF and Excel files — hosted downloads, async jobs, history. | Remote · HTTP |
| DocsSearch and fetch AgendaForge public documentation and marketing content. No authentication needed. | Remote · HTTP |
| DocsSearch and read Empryo's documentation. Read-only, no auth, no local access. | Remote · HTTP |