企业发票OCR识别MCP服务器

基于ModelScope生态构建的专业企业发票OCR识别MCP服务器，为企业财务数字化提供智能化解决方案。

🚀 产品特性

标准化接入：符合MCP协议规范，无缝集成各类AI应用
专业发票识别：支持13种主流发票类型，准确率达99%+
结构化输出：自动提取发票关键信息，输出标准JSON格式
企业级服务：支持批量处理，满足大规模业务需求

📋 支持的发票类型

01: 增值税专用发票
02: 机动车增值税专用发票
03: 增值税普通发票
04: 增值税电子普通发票
05: 增值税普通发票（卷式）
06: 增值税普通发票（通行费）
07: 二手车发票
08: 增值税电子专用发票
09: 数电发票（增值税专用发票）
10: 数电发票（普通发票）
11: 数电发票（航空运输电子客票行程单）
12: 数电发票（铁路电子客票）
13: 区块链发票（支持深圳、北京和云南地区）

🛠️ 安装与启动

环境要求

Python 3.8+
至少4GB内存
推荐GPU支持

快速开始

# 推荐方式：通过PyPI安装
pip install invoice-ocr-mcp

# 启动服务
invoice-ocr-mcp

⚡ MCP平台集成配置（uvx示例）

如需在 MCP 平台集成本服务，推荐使用如下 mcpServers 配置：

{
  "mcpServers": {
    "invoice-ocr-mcp": {
      "command": "uvx",
      "args": [
        "invoice-ocr-mcp"
      ],
      "env": {
        "PYTHONUNBUFFERED": "1"
      }
    }
  }
}

如需自定义环境变量，可在 env 字段补充。

📊 性能指标

识别准确率: >99%
处理速度: 单张发票<3秒
并发支持: 支持多线程并行处理
服务可用性: >99.9%

Metadata

Release files for invoice-ocr-mcp 1.0.4

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for invoice-ocr-mcp 1.0.4
File	Size	Uploaded	Provenance
invoice_ocr_mcp-1.0.4.tar.gz	41.8 kB	Jul 17, 2025	Without provenance	Details

Built distribution (wheel)

Table of built distributions (wheels) for invoice-ocr-mcp 1.0.4
File	Interpreter	ABI	Platform	Reset
invoice_ocr_mcp-1.0.4-py3-none-any.whl 40.8 kB Jul 17, 2025 Without provenance	Python 3	none	any	Details

Total release size: 82.6 kB

Release files / invoice_ocr_mcp-1.0.4.tar.gz

Download URL	invoice_ocr_mcp-1.0.4.tar.gz
Size	41.8 kB
Tags	Source
SHA-256 checksum How to use checksums	`363dec35561a5bb15a33cf386960b3d37bea22a03010211e3046b2509e16925b`
BLAKE2b-256 checksum How to use checksums	`ae3b87bf3f5a0439d1c68d5d86a3793e3fc87e729684a1df446510a0595767fa`
Upload date	Jul 17, 2025
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/6.1.0 CPython/3.10.11`

Release files / invoice_ocr_mcp-1.0.4-py3-none-any.whl

Download URL	invoice_ocr_mcp-1.0.4-py3-none-any.whl
Size	40.8 kB
Tags	Python 3
SHA-256 checksum How to use checksums	`c9ed833b4e58fbfe741dee0d96a9b58c5da3b4b450adf07df6f7714915eb14cf`
BLAKE2b-256 checksum How to use checksums	`0e33669adb0c695361b88730b472f268ed0fafbfcbacfb27cd24e6f521b361f8`
Upload date	Jul 17, 2025
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/6.1.0 CPython/3.10.11`

Security for invoice-ocr-mcp 1.0.4

Report project as malware

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.