Agentic Document Parsing and Extraction (ADP)

by laiye-adp

Not rated
GitHub

Description

ADP automatically classifies overseas invoices, domestic vouchers, procurement contracts, logistics documents, financial statements and trading contracts, and accurately extracts key fields. It also supports table parsing, content verification and multilingual recognition…

About

ADP automatically classifies overseas invoices, domestic vouchers, procurement contracts, logistics documents, financial statements and trading contracts, and accurately extracts key fields. It also supports table parsing, content verification and multilingual recognition. Requiring no template setup, data labeling or…

Details

Author
laiye-adp
Categories
File Management, Other, Finance, Automation, AI

Setup

Install Agentic Document Parsing and Extraction (ADP) in your MCP client (Claude Desktop, Cursor, Windsurf, and others).

Repository: https://github.com/laiye-adp/adp-mcp-nodejs

Follow the installation instructions in the repository README, then restart your MCP client.

Agentic Document Parsing and Extraction (ADP)

ADP automatically classifies overseas invoices, domestic vouchers, procurement contracts, logistics documents, financial statements and trading contracts, and accurately extracts key fields. It also supports table parsing, content verification and multilingual recognition. Requiring no template setup, data labeling or ongoing rule maintenance, it efficiently handles high-volume document processing tasks.

ADP MCP Server is the Model Context Protocol endpoint for Laiye'sAgentic Document Processing (ADP)platform. It lets any MCP-compatible AI client — Claude Desktop, Cursor, Copilot Chat, Tongyi Lingma, Coze, and others — invoke ADP's document parsing and extraction capabilities without writing a single line of code.Unlike the CLI, the MCP Server runs overStreamable HTTPtransport. A single connection is all you need to discover available tools, invoke processing, and query results — entirely within your chat window.

ADP integrates Vision-Language Models (VLM), Large Language Models (LLM) and autonomous agent decision-making technologies. It reshapes traditional document processing by transforming conventional rule-based field extraction into goal-driven end-to-end intelligent automation. Focused on intelligent processing of business documents, ADP automatically classifies overseas invoices, domestic vouchers, procurement contracts, logistics documents, financial statements and trading contracts, and accurately extracts key fields. It also supports table parsing, content verification and multilingual recognition. Requiring no template setup, data labeling or ongoing rule maintenance, it efficiently handles high-volume document processing tasks.

Sign up athttps://adp-global.laiye.com/and retrieve your API Key fromMy MCPin personal settings.

The ADP MCP Server runs overstdiotransport: the client launches a local process vianpxand passes your API Key through an environment variable. Add the following to your client's MCP config file (e.g. Claude Desktop'sclaude_desktop_config.json, Cursor'smcp.json):

{ "mcpServers": { "adp": { "command": "npx", "args": ["-y", "@laiye-adp/mcp"], "env": { "ADP_API_KEY": "<YOUR-ADP-API-Key>" } } } }

The same parameters apply to any MCP client:

The optional environment variableADP_ACCEPT_LANGUAGE(zh/en, defaultzh) switches the API language and domain. Requires Node.js 20+ installed locally.

Once connected, your AI client will automatically discover all available ADP tools. Just describe what you need in natural language:

- "Upload this local file and extract fields from the returned URL"
- "Parse the structure of this PDF"
- "Extract the information from this ID card"
- "Pull the amount and date from this invoice"

In addition to the out-of-the-box tools above, MCP provides two fixed tools for working with custom extraction apps you create on the ADP platform:

Workflow:Calllist_custom_extract_appsto browse available apps and get the targetapp_id, then callexecute_custom_extract_appwith theapp_idand file to perform extraction.

Document Parsing & OOTB Extraction Tools

All out-of-the-box tools share a unified input schema:

The response containsdata.download_url, which can be passed directly to parsing or extraction tools asfile.

- URL: pass a link starting withhttp://orhttps://asfile
- Base64: pass Base64-encoded file content asfile(auto-detected when not a URL)
- Local files: callupload_temporary_filefirst, then pass the returneddata.download_urlto the parsing or extraction tool.

- wait=true(default): blocks until processing completes, returns the result directly
- wait=false: returns immediately with atask_idfor later status queries

{ "code": "success", "message": "", "tips": null, "data": { "id": "ade6dcfd9b9c11f1be34d85ed35661fd", "file_name": "invoice.pdf", "file_size": 123, "content_type": "application/pdf", "download_url": "https://adp.laiye.com/web/agentic_doc_processor/laiye/file/ade6dcfd9b9c11f1be34d85ed35661fd", "status": "success" } }
{ "task_id": "fabd7f0a4e7211f1bbc4d85ed35661fd", "status": 4, "message": "", "doc_recognize_result": [ { "page_num": 1, "document_content": "Full text content of this page...", "document_details": [ { "type": "Text", "text": "Paragraph content...", "position": [{"points": [{"x": 311, "y": 50}, {"x": 500, "y": 50}, {"x": 500, "y": 80}, {"x": 311, "y": 80}]}], "ocr_confidence": { "ocr_mean_confidence": 0.999, "ocr_min_confidence": 0.998, "is_overall_confidence": 1 } }, { "type": "Table", "text": "Column A\tColumn B\nValue 1\tValue 2", "position": [{"points": [...]}], "ocr_confidence": {...} }, { "type": "Picture", "text": "https://adp.laiye.com/web/.../file/abc123", "position": [{"points": [...]}], "ocr_confidence": {...} } ] } ] }
{ "task_id": "91283e544e7111f18cd6d85ed35661fd", "status": 4, "message": "", "extraction_result": [ { "field_key": "invoice_number", "field_name": "Invoice Number", "field_values": [ { "field_value": "24VLT0591617", "field_confidence": 1.0, "references": [] } ] }, { "field_key": "line_items", "field_name": "Product Details", "references": [], "field_confidence": 1.0, "table_values": [ [ { "field_name": "Description", "field_key": "line_items_description", "field_values": [ { "field_value": "TESLA MODEL 3", "field_confidence": 1.0, "references": "Description: TESLA MODEL 3" } ] } ] ] } ] }

How to distinguish:Field object containstable_values→ table field; onlyfield_values→ regular field.

{ "task_id": "fabd7f0a4e7211f1bbc4d85ed35661fd", "status": "running" }

ADP MCP Server uses API Key authentication, passed via theADP_API_KEYenvironment variable:

"env": { "ADP_API_KEY": "<YOUR-ADP-API-Key>" }

- API Key is available from theMy MCPpage in the ADP console
- Each API Key is bound to a single user and can only access that user's apps and data
- The API Key is passed only as an environment variable to the local process and never appears in request bodies or responses

Q: Some card/certificate tools don't appear after connecting?

A: The tool list is dynamically generated based on your initialized apps. On first connection, the system automatically initializes all out-of-the-box apps. Refresh the tool list once initialization completes to see all available tools.

Q: A card tool returns "extraction failed"?

A: Make sure the uploaded file matches the tool type (e.g., useextract_id_cardfor ID card images, notextract_vehicle_cert). The file must be in a supported image or PDF format.

A: The default timeout is 300 seconds (5 minutes). You can adjust it via thetimeout_secondsparameter (max 900). For large files or complex documents, usewait=falsefor async mode and query results later using thetask_id.

Q: How does MCP compare to ADP CLI / OpenAPI?

A: All three provide equivalent functionality — the difference is in the integration method:

- MCP Server: Free to connect, provided as part of the ADP platform
- ADP Service: Cloud-based AI document processing, usage-based billing

Free tier: new users receive100 free creditsper month upon registration

- API Docs:Open API Guide
- Product Manual:
Cloud Operations Manual
- Email:
mkt@laiye.com
- Website:
Laiye

Build the Future of Agentic AI with ❤️Copyright © 2026 [Laiye Technology (Beijing) Co., Ltd.] All rights reserved.

international financial reporting engine for Agents and REST api users journal entries, statement generation, audit trail with workings, financial reporting automation

Automated document processing and extraction

Set up and interact with your unstructured data processing workflows in Unstructured Platform

Interact with your MLOps and LLMOps pipelines through your ZenML MCP server

Contabilidad española con IA: emite facturas, registra gastos por OCR, concilia el banco y prepara el Modelo 303 desde Claude, Cursor o ChatGPT.

Search Brazilian real estate listings, simulate financing, qualify leads, and schedule visits directly from any LLM.

Connect to your CISO Adapt workspace to search, analyse, export, and manage risks and policies with natural language

AI-powered document extraction infrastructure. Convert PDFs, Excel files, and scanned documents into structured JSON.

Free crypto address labels. Identify known addresses on major networks with a free API.

EU Corporate Sustainability Reporting Directive compliance — ESRS data points, double materiality assessments, audit trails, and XBRL-ready outputs for ESG reporting.

No reviews yet — be the first

Sign in to leave a review

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.