{
"mcpServers": {
"mcp-ocr-server": {
"command": "<see-readme>",
"args": []
}
}
}No install config available. Check the server's README for setup instructions.
Are you the author?
Add this badge to your README to show your security score and help users find safe servers.
用于自然语言识别图片内容
Is it safe?
No package registry to scan.
No authentication — any process on your machine can connect.
License not specified.
Is it maintained?
Last commit 128 days ago. 1 stars.
Will it work with my client?
Transport: stdio. Works with Claude Desktop, Cursor, Claude Code, and most MCP clients.
No automated test available for this server. Check the GitHub README for setup instructions.
No known vulnerabilities.
This server is missing a description. Tools and install config are also missing.If you've used it, help the community.
Add informationHave you used this server?
Share your experience — it helps other developers decide.
Sign in to write a review.
Persistent memory using a knowledge graph
Privacy-first. MCP is the protocol for tool access. We're the virtualization layer for context.
Pre-build reality check. Scans GitHub, HN, npm, PyPI, Product Hunt — returns 0-100 signal.
Monitor browser logs directly from Cursor and other MCP compatible IDEs.
MCP Security Weekly
Get CVE alerts and security updates for Mcp Ocr Server and similar servers.
Start a conversation
Ask a question, share a tip, or report an issue.
Sign in to join the discussion.
生产级 OCR MCP Server,基于 Tesseract OCR 和 GoCV,提供智能图像预处理和高性能文本识别服务。
# macOS
./scripts/install-deps.sh
# 或手动安装
brew install tesseract tesseract-lang opencv
make deps
编辑 configs/config.yaml:
server:
name: mcp-ocr-server
version: 1.0.0
ocr:
language: eng+chi_sim+chi_tra+jpn
data_path: /usr/local/share/tessdata
max_image_size: 10485760 # 10MB
timeout: 30
preprocessing:
enabled: true
auto_mode: true # 智能预处理
performance:
worker_pool_size: 4
cache_enabled: true
cache_size: 100
# 构建
make build
# 运行
make run
# 或直接运行
./bin/mcp-ocr-server -config configs/config.yaml
识别图像文件中的文本。
参数:
{
"image_path": "/path/to/image.png",
"language": "eng",
"preprocess": true,
"auto_mode": true
}
返回:
{
"text": "识别的文本内容",
"confidence": 95.5,
"language": "eng",
"duration": 1.23
}
识别 Base64 编码的图像。
参数:
{
"image_base64": "iVBORw0KGgoAAAANSUhEUgA...",
"language": "chi_sim",
"preprocess": true,
"auto_mode": true
}
批量识别多个图像。
参数:
{
"image_paths": [
"/path/to/image1.png",
"/path/to/image2.jpg"
],
"language": "eng+chi_sim",
"preprocess": true
}
返回:
{
"results": [
{
"path": "/path/to/image1.png",
"text": "...",
"confidence": 95.5
},
{
"path": "/path/to/image2.jpg",
"text": "...",
"confidence": 92.3
}
],
"count": 2
}
获取支持的语言列表。
返回:
{
"languages": ["eng", "chi_sim", "chi_tra", "jpn"]
}
在 claude_desktop_config.json 中添加:
{
"mcpServers": {
"ocr": {
"command": "/path/to/mcp-ocr-server",
"args": ["-config", "/path/to/config.yaml"]
}
}
}
用户: 请识别这张图片中的文本 /path/to/document.png
Claude: 我来使用 OCR 工具识别这张图片...
[调用 ocr_recognize_text]
识别结果:
- 文本: "这是一份重要文档..."
- 置信度: 96.5%
- 语言: 简体中文
- 处理时间: 1.2秒
mcp-ocr-server/
├── cmd/
│ └── server/
│ └── main.go # 服务入口
├── internal/
│ ├── config/
│ │ └── config.go # 配置管理
│ ├── ocr/
│ │ ├── engine.go # OCR 引擎接口
│ │ └── tesseract.go # Tesseract 实现
│ ├── preprocessing/
│ │ ├── analyzer.go # 图像质量分析
│ │ └── preprocessor.go # 图像预处理
│ ├── pool/
│ │ └── worker_pool.go # Worker Pool
│ ├── cache/
│ │ └── cache.go # 结果缓存
│ ├── tools/
│ │ ├── schemas.go # MCP Tool Schema
│ │ └── handler.go # Tool Handler
│ └── server/
│ └── server.go # MCP Server
├── pkg/
│ ├── errors/
│ │ └── errors.go # 错误处理
│ └── logger/
│ └── logger.go # 日志封装
├── configs/
│ └── config.yaml # 配置文件
├── scripts/
│ └── install-deps.sh # 依赖安装脚本
├── Makefile # 构建管理
├── Dockerfile # Docker 支持
└── README.md # 项目文档
ocr:
language: eng+chi_sim # 语言组合
data_path: /path/to/tessdata # tessdata 路径
page_seg_mode: 3 # 页面分割模式
max_image_size: 10485760 # 最大图像大小
timeout: 30 # 超时时间
preprocessing:
enabled: true
... [View full README on GitHub](https://github.com/Ricardo-M-L/mcp-ocr-server#readme)