OCR MCP Server
MCP (Model Context Protocol) 服务器,让 Claude Code / Cursor / Windsurf 等 AI 编码工具通过 MCP 协议直接调用 OCR 文字识别服务。
功能
| Tool | 说明 |
|---|---|
ocr_recognize |
图片文字识别 - 从任意包含文字的图片中提取文本内容 |
ocr_table |
表格识别 - 从图片中提取表格的行列结构化数据 |
ocr_health |
服务健康检查 - 验证后端 OCR 服务是否正常运行 |
参数说明
ocr_recognize 和 ocr_table 支持以下参数(三选一,优先级从高到低):
| 参数 | 说明 |
|---|---|
image_path |
本地文件路径(推荐) - 支持 png, jpg, jpeg, gif, bmp, webp, tiff, tif, pdf |
image_base64 |
图片的 base64 编码 |
image_url |
图片 URL 地址 |
直接给文件路径即可,MCP Server 会自动读取文件并处理。
环境变量
| 变量 | 默认值 | 说明 |
|---|---|---|
OCR_SERVICE_URL |
http://127.0.0.1:8082/api |
OCR 后端 API 地址(含路径前缀) |
接入配置
Claude Code
项目根目录创建 .mcp.json:
{
"mcpServers": {
"ocr": {
"command": "uvx",
"args": ["wk-ocr-mcp"],
"env": {
"OCR_SERVICE_URL": "https://gogs.wxapp.info/ocr-api"
}
}
}
}
或 pip install 后:
{
"mcpServers": {
"ocr": {
"command": "python3",
"args": ["-m", "ocr_mcp_server"],
"env": {
"OCR_SERVICE_URL": "https://gogs.wxapp.info/ocr-api"
}
}
}
}
Cursor / Windsurf
分别放到项目根目录 .cursor/mcp.json 或 .codeium/windsurf/mcp_config.json,格式同上。
OCR_SERVICE_URL 配置说明
OCR_SERVICE_URL 必须指向 API 路径前缀:
| 场景 | 值 |
|---|---|
| 直接访问 | http://127.0.0.1:8082/api |
| Nginx 代理 | https://gogs.wxapp.info/ocr-api |
代码会在此基础拼接端点:{URL}/ocr、{URL}/table、{URL}/health
使用方式
配置好后重启工具,直接用自然语言:
帮我识别这张图片里的文字: /path/to/screenshot.png
这个截图里的表格数据提取出来: /path/to/table.png
AI 会自动调用 ocr_recognize 或 ocr_table,传入文件路径即可完成识别。
License
MIT
Metadata
Release files for wk-ocr-mcp 0.2.2
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | |
|---|---|---|---|---|
| wk_ocr_mcp-0.2.2.tar.gz | 3.8 kB | Without provenance | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| wk_ocr_mcp-0.2.2-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 8.9 kB
Release files / wk_ocr_mcp-0.2.2.tar.gz
| Download URL | wk_ocr_mcp-0.2.2.tar.gz |
|---|---|
| Size | 3.8 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
8792b32dc15444669dc80bb73c4794747213ff29d7f607e5ddb37e7d240cb973
|
|
BLAKE2b-256 checksum How to use checksums |
ee29ec50154e0a55fec6319c5e925956bf630c3bef8ad421118419e6259afb68
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.11.15
|
Release files / wk_ocr_mcp-0.2.2-py3-none-any.whl
| Download URL | wk_ocr_mcp-0.2.2-py3-none-any.whl |
|---|---|
| Size | 5.1 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
8808d9656e9744d52fbd77eb34860f7ece3451b0b6a51251dc1f5263d1464912
|
|
BLAKE2b-256 checksum How to use checksums |
777ffcff7afe247564996afb607631a8cdb7cf7a8753d8af93df9e05cbd7b5d3
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.11.15
|
Security for wk-ocr-mcp 0.2.2
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.