Docpick MCP server
✓ VerifiedMengekstrak JSON terstruktur dari dokumen menggunakan engine OCR lokal dan LLM dengan skema Pydantic yang dapat disesuaikan.
Juga dikenal sebagai QuartzUnit/docpick
- Stars
- 1
- Tools
- —
- Unduhan, 30 hari
- 2.671
- Versi terbaru
- 0.1.2
- Commit terakhir
- 15 Apr 2026
- Lisensi
- Apache-2.0
Apa itu Docpick MCP?
Docpick adalah MCP server. Mengekstrak JSON terstruktur dari dokumen menggunakan engine OCR lokal dan LLM dengan skema Pydantic yang dapat disesuaikan.
Ringkasan dibuat dari README proyek
Tentang Docpick MCP server
Docpick memungkinkan developer yang membangun pipeline data privat untuk mengubah dokumen fisik menjadi data JSON terstruktur secara lokal. Sistem ini berfungsi sebagai sistem ekstraksi berbasis skema yang menggabungkan engine OCR lokal seperti PaddleOCR, EasyOCR, atau GOT-OCR2.0 dengan endpoint LLM lokal seperti Ollama atau vLLM. Konfigurasi ini memastikan informasi sensitif dari invoice, struk, atau rekening koran tidak pernah meninggalkan mesin Anda, karena seluruh proses berjalan pada CPU atau GPU Anda sendiri.
Pengguna dapat memilih dari delapan skema bawaan untuk dokumen umum atau menentukan model Pydantic kustom untuk menerapkan struktur data tertentu. Sistem ini menyertakan tool validasi bawaan seperti verifikasi checkdigit untuk IBAN atau nomor bisnis Korea serta aturan cross-field untuk memastikan konsistensi matematis. Baik memproses satu file melalui Python API atau menjalankan batch job di seluruh direktori dengan parallel workers, pipeline ini mengelola fallback OCR dan retry LLM untuk menjaga akurasi ekstraksi yang tinggi.
Apa yang bisa Anda lakukan dengannya
- 1Ekstraksi data invoiceMengonversi invoice komersial menjadi JSON terstruktur sambil memverifikasi tax ID dan total jumlah item.
- 2Validasi dokumen identitasMengekstrak informasi paspor dan memverifikasinya terhadap standar ICAO 9303 dan zona MRZ.
- 3Otomatisasi pemrosesan dokumen batchMenjalankan tugas ekstraksi secara paralel pada folder berisi banyak dokumen menggunakan skema tertentu.
- 4Memastikan konsistensi antar dokumenMemverifikasi bahwa data tetap konsisten di seluruh invoice, bill of lading, dan packing list.
Ditulis berdasarkan README proyek. Setiap use case diperiksa terhadap kutipan dari README tersebut.
Cara menginstal Docpick MCP
Format diverifikasi 10 Nov 2026Tambahkan ke CursorTambahkan ke GooseInstal Docpick MCP di Claude Code
$ claude mcp add docpick -- uvx docpickInstal Docpick MCP di Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"docpick": {
"command": "uvx",
"args": [
"docpick"
]
}
}
}Instal Docpick MCP di VS Code
.vscode/mcp.json
{
"servers": {
"docpick": {
"type": "stdio",
"command": "uvx",
"args": [
"docpick"
]
}
}
}Instal Docpick MCP di VS Code CLI
$ code --add-mcp '{"name":"docpick","type":"stdio","command":"uvx","args":["docpick"]}'Instal Docpick MCP di Claude Desktop
claude_desktop_config.json
{
"mcpServers": {
"docpick": {
"command": "uvx",
"args": [
"docpick"
]
}
}
}Instal Docpick MCP di Codex
$ codex mcp add docpick -- uvx docpickInstal Docpick MCP di Codex config.toml
~/.codex/config.toml
[mcp_servers.docpick] command = "uvx" args = ["docpick"]
Instal Docpick MCP di Gemini CLI
$ gemini mcp add -s user docpick uvx -- docpickInstal Docpick MCP di Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"docpick": {
"command": "uvx",
"args": [
"docpick"
]
}
}
}Pengecekan otomatis
Berjalan 15 Nov 2026Laporan lengkap →Lolos checks otomatis kami. Ini bukan audit keamanan: baca kodenya dan berikan server akses paling terbatas yang dibutuhkannya. Cara kerja checks
- Source repository terhubung dan dapat dijangkauquartzunit/docpick is public and reachablegithub.com/quartzunit/docpick ↗Lolos
- Nama paket mencantumkan repositori ini sebagai sumbernyadocpick names quartzunit/docpick as sourcepypi.org/project/docpick/ ↗Lolos
- Provenance build (atestasi Sigstore)No build attestation published for this releaseTidak diperiksa
- Lisensi open source (OSI)Apache-2.0spdx.org/licenses/Apache-2.0.html ↗Lolos
- Ada commit atau release dalam satu tahun terakhirLast commit or release 2026-04-15github.com/quartzunit/docpick ↗Lolos
- OpenSSF ScorecardTidak diperiksa
- Nama package tidak mirip dengan package populerNo popular package one edit away from docpickLolos
- Tidak ada advisory kritis pada paket atau dependensinya22 resolved dependencies checked; no critical advisoryosv.dev ↗Lolos
- Tidak ada instruksi tersembunyi untuk model0 tool descriptions and the README read; no override phrases, credential paths or hidden charactersLolos
- Tools yang bersifat destruktif telah diberi labelTidak diperiksa
- Endpoint remote merespons handshake MCPTidak diperiksa
README
Lihat di GitHubDocpick
Document in, Structured JSON out. Locally. With your schema.
docpick is a lightweight, schema-driven document extraction pipeline that combines local OCR engines with local LLMs to extract structured JSON from any document — invoices, receipts, bills of lading, tax forms, and more.
- Zero cloud dependency — runs entirely on your machine (CPU or GPU)
- Custom schemas — define your own Pydantic models or use 8 built-in document schemas
- Validation built-in — checkdigit verification, cross-field rules, cross-document consistency
- Apache 2.0 — no GPL/AGPL dependencies
Install
pip install docpick # core (LLM extraction only)
pip install docpick[paddle] # + PaddleOCR (recommended)
pip install docpick[easyocr] # + EasyOCR (Korean-optimized)
pip install docpick[got] # + GOT-OCR2.0 (GPU, vision-language)
pip install docpick[all] # all OCR backends
Requirements: Python 3.11+ / LLM endpoint (vLLM, Ollama, or OpenAI-compatible)
Quick Start
Python API
from docpick import DocpickPipeline
from docpick.schemas import InvoiceSchema
pipeline = DocpickPipeline()
result = pipeline.extract("invoice.pdf", schema=InvoiceSchema)
print(result.data) # Structured dict matching schema
print(result.validation) # Validation errors/warnings
print(result.confidence) # Per-field confidence scores
CLI
# Extract structured data
docpick extract invoice.pdf --schema invoice --output result.json
# OCR only (no LLM)
docpick ocr document.png --lang ko,en
# Validate extracted JSON
docpick validate result.json --schema invoice
# Batch process a directory
docpick batch ./documents/ --schema invoice --output ./results/ --concurrency 4
# List available schemas
docpick schemas list
# Show schema details
docpick schemas show invoice
Built-in Schemas
| Schema | Document Type | Key Validations |
|---|---|---|
invoice |
Commercial invoices | Line item sums, tax ID checkdigit, date order |
receipt |
Retail/restaurant receipts | Total = subtotal + tax + tip |
bill_of_lading |
Ocean/air B/L | Container weight sums, ISO 6346, HS code format |
purchase_order |
Purchase orders | PO total = line items, delivery date order |
kr_tax_invoice |
Korean e-tax invoice (세금계산서) | Business number checkdigit (x2), supply/tax/total sums |
bank_statement |
Bank statements | IBAN mod97, period date order |
id_document |
Passport/ID (ICAO 9303) | MRZ, ISO 3166 country codes, date ranges |
certificate_of_origin |
Certificate of Origin | ISO 3166 alpha-2 country codes |
Custom Schemas
Define your own schema with Pydantic:
from pydantic import BaseModel
from docpick import DocpickPipeline
from docpick.validation.rules import SumEqualsRule, RequiredFieldRule
class MyDocument(BaseModel):
"""Custom document schema."""
company_name: str | None = None
total_amount: float | None = None
tax_amount: float | None = None
net_amount: float | None = None
items: list[dict] | None = None
class ValidationRules:
rules = [
RequiredFieldRule("company_name"),
SumEqualsRule(["net_amount", "tax_amount"], "total_amount"),
]
pipeline = DocpickPipeline()
result = pipeline.extract("my_document.pdf", schema=MyDocument)
Or use a JSON Schema file:
docpick extract document.pdf --schema my_schema.json
Validation
Check Digit Algorithms
| Algorithm | Use Case |
|---|---|
kr_business_number |
Korean business registration number (10 digits) |
luhn |
Credit card numbers |
iso_6346 |
Shipping container numbers |
iban_mod97 |
International bank account numbers |
awb_mod7 |
Air waybill numbers |
mrz |
Machine Readable Zone (passport/ID) |
Cross-Field Rules
| Rule | Description |
|---|---|
SumEqualsRule |
Sum of fields equals target (with tolerance) |
DateBeforeRule |
Date A must precede Date B |
RequiredFieldRule |
Field must be non-null and non-empty |
FieldEqualsRule |
Two fields must be equal |
RangeRule |
Numeric field within min/max bounds |
RegexRule |
Field matches regex pattern |
Cross-Document Validation
Validate consistency across related documents (e.g., Invoice + B/L + Packing List):
from docpick.validation.cross_document import create_trade_document_validator
validator = create_trade_document_validator()
result = validator.validate({
"invoice": invoice_data,
"bl": bl_data,
"packing_list": packing_list_data,
"certificate": certificate_data,
})
print(result.is_valid)
OCR Engines
| Engine | Type | GPU | Languages | Best For |
|---|---|---|---|---|
| PaddleOCR | Traditional OCR | Optional | 111 | General documents (default) |
| EasyOCR | Traditional OCR | Optional | 80+ | Korean text |
| GOT-OCR2.0 | Vision-Language | Required | Multi | Complex layouts |
| VLM | Vision-Language | Required | Multi | Direct image → JSON |
2-Tier Auto Engine
The default auto engine uses confidence-based fallback:
- Tier 1 (CPU): PaddleOCR → EasyOCR
- Tier 2 (GPU): GOT-OCR2.0 → VLM
If Tier 1 average confidence falls below threshold (default 0.7), automatically escalates to Tier 2.
LLM Providers
| Provider | Endpoint | Default Model |
|---|---|---|
| vLLM | http://localhost:8000/v1 |
Qwen/Qwen3.5-32B-AWQ |
| Ollama | http://localhost:11434 |
qwen3.5:7b |
Configure via CLI or YAML:
docpick config set llm.provider ollama
docpick config set llm.base_url http://localhost:11434
docpick config set llm.model qwen3.5:7b
Error Handling
The pipeline is designed to be resilient:
- OCR failure → automatic fallback to next available engine
- LLM JSON parse failure → automatic retry with correction prompt (up to 1 retry)
- Partial results → returns whatever was extracted, with errors logged in
result.errors - Document load failure → returns empty result with error message
result = pipeline.extract("damaged.pdf", schema=InvoiceSchema)
if result.errors:
print("Pipeline warnings:", result.errors)
if result.data:
print("Partial extraction:", result.data)
Batch Processing
Process entire directories with parallel workers:
from docpick.batch import BatchProcessor
from docpick.schemas import InvoiceSchema
processor = BatchProcessor(concurrency=4)
result = processor.process_directory(
"./invoices/",
schema=InvoiceSchema,
recursive=True,
)
print(f"Processed {result.succeeded}/{result.total} files")
for path, extraction in result.results.items():
print(f"{path}: {extraction.data.get('total_amount')}")
Architecture
flowchart TD
A["📄 Document\n(PDF / Image)"] --> B["DocumentLoader\n(pypdfium2)"]
B --> C["Tier 1: OCR\n(PaddleOCR / EasyOCR)\nCPU"]
C --> D{"Confidence\n≥ threshold?"}
D -->|"yes"| F["LLM Extractor\n(vLLM / Ollama)\nSchema prompt"]
D -->|"no"| E["Tier 2: VLM\n(GOT / VLM)\nGPU"]
E --> F
F --> G["Pydantic Validation"]
G --> H["✅ ExtractionResult"]
License
Apache 2.0 — all dependencies are Apache 2.0 or MIT licensed.
Part of the QuartzUnit ecosystem — composable Python libraries for data collection, extraction, search, and AI agent safety.
Pertanyaan tentang Docpick MCP
Bagaimana cara menambahkan Docpick MCP ke Claude Code?
Jalankan claude mcp add docpick -- uvx docpick di terminal Anda. Tambahkan --scope user agar tersedia di semua proyek.
Bagaimana cara menambahkan Docpick MCP ke Cursor?
Buka ~/.cursor/mcp.json dan tambahkan server di bawah mcpServers, menggunakan config Cursor yang ditunjukkan di bagian instalasi di atas.
Apakah Docpick memerlukan layanan cloud?
Tidak, Docpick berjalan sepenuhnya di mesin Anda tanpa ketergantungan pada cloud.
Bisakah saya menggunakan struktur data saya sendiri untuk ekstraksi?
Ya, Anda dapat menentukan skema sendiri menggunakan model Pydantic atau file JSON Schema.
Bagaimana sistem menangani hasil OCR dengan tingkat kepercayaan rendah?
Sistem menggunakan engine auto 2-tier yang secara otomatis beralih ke vision-language model yang lebih canggih jika tingkat kepercayaan turun di bawah ambang batas tertentu.