Skip to main content
Glama

OCR MCP Service

中文 | 日本語

MCP service for OCR tasks powered by PaddleOCR.

Features

  • Text recognition from images

  • Table recognition with simple structured output

  • Handwriting recognition

  • Formula recognition with LaTeX output

  • Local file paths and HTTP/HTTPS URLs

  • MCP stdio server for desktop or agent integrations

Related MCP server: openai-vision-mcp-server

Installation

From PyPI

pip install ocr-mcp

From source

git clone https://github.com/LinuxLinking/OCR_MCP.git
cd OCR_MCP
pip install -e .

Usage

Run the MCP server:

ocr-mcp

Or:

python -m ocr_mcp

Claude Desktop

Add this to your Claude Desktop config:

{
  "mcpServers": {
    "ocr": {
      "command": "ocr-mcp",
      "args": []
    }
  }
}

Tools

ocr_recognize

Recognize text in an image.

  • source required, local path or URL

  • language optional, default ch, supports ch, en, japan, korean

  • use_angle_cls optional, default true

ocr_table

Recognize a table and return a text table.

  • source required, local path or URL

  • language optional, default ch

ocr_handwrite

Recognize handwriting in an image.

  • source required, local path or URL

  • language optional, default ch

ocr_formula

Recognize formulas and return LaTeX.

  • source required, local path or URL

Development

pip install -e ".[dev]"
pytest tests/ -v

Project Layout

src/ocr_mcp/
  __init__.py
  __main__.py
  server.py
  ocr_engine.py
  table_parser.py
  formula_engine.py
  utils.py
tests/
pyproject.toml
LICENSE
README.md

Dependencies

  • PaddleOCR

  • PaddlePaddle

  • OpenCV

  • MCP

License

MIT. See LICENSE.

Available Tools

4 tools
ocr_formulaA

识别图片中的数学公式,返回 LaTeX 格式。

Inputs: source (required).

ocr_handwriteB

识别图片中的手写文字内容。

Inputs: source (required), language.

ocr_recognizeC

识别图片中的文字内容。支持本地文件路径或 URL。

Inputs: source (required), language, use_angle_cls.

ocr_tableC

识别图片中的表格内容,返回结构化的表格数据。

Inputs: source (required), language.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A3.5/5.0

    Scored across 4 tools

    Disambiguation4/5

    The tools are mostly clearly separated by content type: general text, tables, handwriting, and formulas. There is minor overlap because ocr_recognize could plausibly also handle handwritten text or tables, but the specialized tools make their intended use clear.

    Naming Consistency4/5

    All tools share the consistent ocr_ prefix, which makes the server easy to scan. The suffixes mix verbs and nouns (recognize/handwrite vs table/formula), but the pattern remains predictable and readable.

    Tool Count5/5

    Four tools is well-scoped for an OCR server: one general recognition tool plus three specialized modes. Each tool has a clear reason to exist without overwhelming the agent.

    Completeness4/5

    The surface covers the main OCR use cases: plain text, tables, handwriting, and formulas. Minor gaps such as batch processing, PDF input, or language options exist, but they are not essential for the apparent core purpose.

    Maintenance

    ActivityMaintained
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • F
      license
      Not graded
      quality
      D
      maintenance
      Provides OCR services powered by Google's Gemini API to extract text from images via file paths or base64 strings. It enables high-accuracy text recognition and CAPTCHA processing through simple MCP tools.
      8
      -
    • A
      license
      Not graded
      quality
      C
      maintenance
      Enables image analysis via OpenAI-compatible vision APIs, supporting local files, URLs, and base64 inputs with intelligent tiling for high-resolution images. Provides a secure, configurable MCP stdio server for structured vision analysis.
      91 npm
      3
      MIT
    • F
      license
      Not graded
      quality
      D
      maintenance
      Provides OCR (Optical Character Recognition) capabilities through MCP, including text extraction and document layout parsing to Markdown. Supports multiple PaddleOCR models like PP-OCRv5, PP-OCRv6, and PP-StructureV3.
      -