execute_custom_extract_app
使用指定的自定义文档抽取应用处理文件。需先通过 list_custom_extract_apps 获取可用的 app_id。
LABSCO SUMMARY
A dedicated tool per document type, which is why the output is named fields rather than a wall of text.
Each certificate and bill has an extractor that already knows that document's fields, so what comes back is a field key, a human-readable name and a confidence score you can threshold on. The trade is that routing matters: send an ID card to the vehicle-certificate tool and it reports an extraction failure, so pick by document type first and fall back to parse_document only when the type is genuinely unknown. Two practical notes — the tool list is generated from the apps initialised on your account, so refresh it once after the first connection if a certificate tool is missing, and run large files with wait=false and collect them with query_task and get_result rather than holding a call open for five minutes.
What it is
The MCP endpoint for Laiye's Agentic Document Processing platform. One tool parses any PDF, image or Office file into structured blocks with page coordinates; the rest are purpose-built extractors for Chinese bills and certificates, overseas and Southeast Asian invoices, and purchase orders. There are no templates to define, no fields to label and no rules to maintain.
What you get
- parse_document handles PDF, image, Word, Excel and PPT, returning text blocks, tables and pictures in reading order with four-corner bounding boxes and per-element OCR confidence
- extract_china_invoice covers 30+ Chinese bill types — fully-digitalised e-invoices, general and special VAT invoices, taxi receipts, train tickets, air itineraries, fiscal invoices — and can also judge whether an invoice is genuine
- extract_global_invoice reads number, date, amount, tax, currency and line items from overseas invoices and receipts; extract_global_invoice_fast and extract_sea_invoice_fast skip the OCR stage and go straight to the vision model for latency-sensitive batches, the Southeast Asian one adding withholding-tax fields
- Chinese identity and company documents each get their own extractor: extract_id_card, extract_business_license, extract_driver_license, extract_vehicle_license, extract_vehicle_cert, extract_passport_cn, extract_hk_macao_permit, extract_household_book, extract_bank_card, extract_account_permit and extract_org_code_cert
- extract_purchase_order pulls order number, both parties, order date, item details, quantity, unit price, total and shipping address out of purchase and sales orders
- Every extraction answers with field_key, field_name and a field_confidence between 0 and 1 per value; table fields arrive as table_values, a two-dimensional array of cells you can tell apart because plain fields have only field_values
- Local files go up through upload_temporary_file, which returns a data.download_url to pass as the file parameter; a plain URL or Base64 content works without that step
- list_custom_extract_apps and execute_custom_extract_app run the extraction apps you built on the platform yourself, using the output field definitions each app declares
- query_task and get_result collect work that was started asynchronously
Requirements
Runs over stdio as npx -y @laiye-adp/mcp and needs Node.js 20+ locally. ADP_API_KEY comes from the My MCP page in the ADP console, is bound to one user's apps and data, and is passed only as an environment variable — it never appears in request bodies or responses. ADP_ACCEPT_LANGUAGE switches between zh and en and defaults to zh. Calls wait for the result by default and time out at 300 seconds; timeout_seconds accepts up to 900, or wait=false returns a task_id to poll. New accounts receive 100 free credits a month, and the service is billed by usage after that.
Setup effort
One command plus a key — npx -y @laiye-adp/mcp, then supply credentials
USE CASES
01
Getting the numbers off a stack of Chinese invoices
Upload the file, then extract invoice number, date, amount, buyer and seller across whichever of the 30+ bill types it turns out to be — with an authenticity check in the same call.
02
Onboarding a supplier from their paperwork
Read the business licence for the company name, unified social credit code, legal representative and registered address, and the bank account permit for the account the payments will go to.
03
Verifying a driver before they start work
Licence class, first issue date and validity from the driver licence, plate, VIN and owner from the vehicle licence, both sides of each document supported.
04
Processing cross-border invoices in bulk
Number, date, amount, tax, currency and line items from overseas receipts. When latency matters more than the OCR intermediate results, the fast variants go straight to the vision model.
05
Handling a document type nobody built a tool for
Parse the layout first and work from the structured text blocks, tables and coordinates — or run an extraction app you defined yourself on the platform.
06
Running a big batch without blocking the session
Start the job without waiting, keep the task ID, and pick the finished result up later instead of holding a five-minute call open.
21 tools
Counted once with only startup setup. Other versions, modes or optional credentials may expose a different list.
extract_account_permit
从企业开户许可证图片中提取关键字段（企业名称、基本账户账号、开户银行、核准号、发证日期等）。适用于对公收款账户校验、企业财务审核、应付账款收款方信息核对等场景。
extract_bank_card
从银行卡正面图片中提取关键字段（卡号、所属银行、卡种类型、有效期等）。适用于绑卡、收款账户录入、支付渠道配置等场景。注意：仅识别卡面公开信息，不涉及 CVV 等敏感字段。
extract_business_license
从中国企业营业执照图片中提取关键字段（企业名称、统一社会信用代码、法定代表人、注册资本、成立日期、经营范围、注册地址等）。适用于企业开户、商户入驻、供应商资质审核、企业实名认证等场景。
extract_china_invoice
覆盖中国地区 30+ 种常见票据：支持全电发票、普通发票、专用发票、出租车票、火车票、飞机行程单、财政发票等财务场景常见票据。可从票据中提取发票号码、开票日期、金额、购买方、销售方等关键信息，以及支持判断发票真假。
extract_driver_license
从中国机动车驾驶证图片中提取关键字段（姓名、性别、国籍、出生日期、驾驶证号、准驾车型、初次领证日期、有效期等），支持正副页识别。适用于驾驶员资质核验、网约车/货运司机准入审核等场景。
extract_global_invoice
从 PDF 或图片格式的海外发票、收据、票据中提取关键字段（发票号、开票日期、金额、税额、币种、明细行等）。适用于跨境贸易、报销、应付账款自动化等场景；中国大陆增值税发票请使用专门的国内发票工具。
extract_global_invoice_fast
从 PDF 或图片格式的海外发票、收据中高速提取关键字段（发票号、开票日期、金额、税额、币种、明细行等）。跳过 OCR 阶段，直接使用 VLM 提取，速度更快；适用于对延迟敏感的批量处理场景；中国大陆增值税发票请使用国内票据工具。
extract_hk_macao_permit
从港澳通行证（往来港澳通行证）图片中提取关键字段（姓名、性别、出生日期、证件号、签发日期、有效期、签发机关等）。适用于出入境业务、酒店登记、票务实名等场景。
extract_household_book
从中国居民户口本图片中提取关键字段（户号、户别、住址、家庭成员列表，含成员姓名、身份证号、与户主关系等），支持首页与个人页两种页面类型。适用于户籍核验、亲属关系认证、社保业务等场景。
extract_id_card
从中国大陆居民身份证图片中提取关键字段（姓名、性别、民族、出生日期、身份证号、住址、签发机关、有效期等），支持正反面识别。适用于实名认证、用户注册等场景；港澳台、护照等其他证件请使用对应工具。
extract_org_code_cert
从组织机构代码证图片中提取关键字段（机构名称、组织机构代码、法定代表人、地址、发证日期、有效期等）。适用于历史档案数字化、存量企业资质核验等场景；新办企业建议使用营业执照工具，组织机构代码已并入统一社会信用代码。
extract_passport_cn
从中华人民共和国护照图片中提取关键字段（中文姓名、姓名拼音、性别、出生日期、护照号、国籍、签发日期、有效期、签发机关等）。适用于出境业务、跨境身份核验、签证办理等场景；外国护照不在支持范围内。
extract_purchase_order
从 PDF 或图片格式的采购订单、销售订单中提取关键字段（订单号、买卖双方信息、下单日期、商品明细、数量、单价、总金额、收货地址等）。适用于电商订单录入、供应链对账、出入库管理自动化等场景。
extract_sea_invoice_fast
从 PDF 或图片格式的东南亚地区发票、收据中高速提取关键字段，支持 WHT（预扣税）等东南亚特有字段。跳过 OCR 阶段，直接使用 VLM 提取；适用于泰国、越南、印尼等东南亚国家的发票处理场景。
extract_vehicle_cert
从机动车整车出厂合格证图片中提���关键字段（合格证编号、车辆品牌、型号、车辆识别代号 VIN、发动机号、制造日期等）。适用于车辆上户、二手车交易、车辆资产管理等场景。
extract_vehicle_license
从中国机动车行驶证图片中提取关键字段（车牌号、车辆类型、所有人、车辆识别代号 VIN、发动机号、注册日期、发证日期等），支持正副页识别。适用于车辆登记、保险投保、网约车/货运车辆准入等场景。
get_result
获取已完成的文档处理任务的完��结果
list_custom_extract_apps
列出当前用户创建的所有自定义文档抽取应用，返回每个应用的 ID、名称、描述、标签和输出字段定义。可用于查找 execute_custom_extract_app 所需的 app_id。
parse_document
对 PDF、图片、Word、Excel、PPT 等文档进行版面解析，返回结构化的文本块、表格、阅读顺序与页面坐标。适用于不确定文档类型、需要先获取原始结构再做后续处理的场景；如已确认是发票、证件等特定类型，请优先使用对应的专用提取工具。
query_task
查询文档处理任务的当前状态
BEFORE YOU INSTALL
What to know first
Tools you get
21 tools when we connected; the project documents 22. The tool list is generated from your initialized apps; refresh it after first-connection initialization finishes to see all tools. The server runs over stdio, as every config block shows.
Requires
- npx on PATH
- ADP_API_KEY in your environment
Where it runs
All 4 documented clients run the server on your machine.
INSTALLATION
Connect your client
Server setup
TERMINAL
npx -y @laiye-adp/mcpMCP Clients
Claude Desktop, Cursor, Coze, Other MCP clients
JSON
{
"mcpServers": {
"adp": {
"command": "npx",
"args": [
"-y",
"@laiye-adp/mcp"
],
"env": {
"ADP_API_KEY": "<YOUR_ADP_API_KEY>"
}
}
}
}
