# CubeParser MCP Server
A Model Context Protocol (MCP) server that provides access to CubeParser document extraction API. This server can be run directly using `uvx` with absolute paths for easy deployment and sharing.
## 🚀 Quick Start with uvx
### For End Users (Running the Server)
If someone has shared this project with you, you can run it directly using uvx with the absolute path:
```bash
# Replace with the actual absolute path provided to you
uvx --from "C:\path\to\cubeparser_mcp" cubeparser-mcp
```
**Example:**
```bash
uvx --from "C:\Users\Remy\sensedeal\code\projects\work\CITICS2025\zhangkai\cubeparser_mcp" cubeparser-mcp
```
### For Developers (Setting Up for Sharing)
1. **Clone and Setup**:
```bash
git clone <repository-url>
cd cubeparser_mcp
uv sync
```
2. **Run Setup Script**:
```bash
uv run python setup_uvx.py
```
This creates:
- `mcp_config.json` - MCP client configuration with absolute paths
- `.env.template` - Environment variables template
- `run_cubeparser_mcp.bat` - Quick run script for Windows
3. **Configure Environment**:
```bash
cp .env.template .env
# Edit .env with your CubeParser credentials
```
## 📋 Features
This MCP server provides three main tools:
1. **get_templates** - Retrieve available extraction templates from CubeParser
2. **create_task** - Upload files and create extraction tasks with specified templates
3. **download_results** - Get extraction results from completed tasks
## 🛠️ Installation Methods
### Method 1: Direct uvx Usage (Recommended for Sharing)
```bash
# Run from absolute path (replace with actual path)
uvx --from "/absolute/path/to/cubeparser_mcp" cubeparser-mcp
# Or on Windows
uvx --from "C:\absolute\path\to\cubeparser_mcp" cubeparser-mcp
```
### Method 2: Local Development
```bash
# Install dependencies
uv sync
# Run directly
uv run python main.py
# Or use the generated batch file
.\run_cubeparser_mcp.bat # Windows
./run_cubeparser_mcp.sh # Linux/Mac
```
## ⚙️ Configuration
### Environment Variables
Create a `.env` file with your CubeParser credentials:
```env
CUBEPARSER_USERNAME=your_username_here
CUBEPARSER_PASSWORD=your_password_here
CUBEPARSER_BASEURL=https://cubeparser.cn/
```
### MCP Client Configuration
Use the generated `mcp_config.json` file in your MCP client (e.g., Claude Desktop):
```json
{
"mcpServers": {
"cubeparser": {
"command": "uvx",
"args": [
"--from",
"C:\\absolute\\path\\to\\cubeparser_mcp",
"cubeparser-mcp"
],
"env": {
"CUBEPARSER_USERNAME": "your_username",
"CUBEPARSER_PASSWORD": "your_password",
"CUBEPARSER_BASEURL": "https://cubeparser.cn/"
}
}
}
}
```
## 🔧 Available Tools
### get_templates()
Retrieves a list of available extraction templates from CubeParser.
**Returns:** List of template objects with IDs, names, and descriptions.
### create_task(file_path: str, template_id: str)
Creates an extraction task by uploading a file and specifying a template.
**Parameters:**
- `file_path`: Absolute path to the file to be processed
- `template_id`: ID of the template to use for extraction
**Returns:** Task information including task ID and status.
### download_results(task_id: str)
Downloads extraction results for a completed task.
**Parameters:**
- `task_id`: ID of the extraction task
**Returns:** Extraction results and task status information.
## 🧪 Testing
### Test the Installation
```bash
# Test that the server starts correctly
uvx --from "C:\your\absolute\path\to\cubeparser_mcp" cubeparser-mcp
# Or use the batch file
.\run_cubeparser_mcp.bat
```
### Run Tests
```bash
uv run pytest
```
## 📁 Generated Files
After running `setup_uvx.py`, you'll have:
- **`mcp_config.json`** - Ready-to-use MCP client configuration
- **`.env.template`** - Template for environment variables
- **`run_cubeparser_mcp.bat`** - Windows batch script for easy testing
- **`run_cubeparser_mcp.sh`** - Linux/Mac shell script for easy testing
## 🚨 Troubleshooting
### Common Issues
1. **Server won't start**: Check that environment variables are set correctly
2. **uvx command not found**: Install uv first: `pip install uv`
3. **Permission errors**: Ensure the absolute path is accessible
4. **Network errors**: Verify CubeParser API credentials and network access
### Debug Mode
Run with verbose logging:
```bash
uvx --from "C:\your\path\to\cubeparser_mcp" cubeparser-mcp --verbose
```
## 📤 Sharing with Others
To share this MCP server with others:
1. **Provide the absolute path** to your project directory
2. **Share the uvx command**:
```bash
uvx --from "C:\your\absolute\path\to\cubeparser_mcp" cubeparser-mcp
```
3. **Include environment setup instructions** (they need their own CubeParser credentials)
## 📄 License
MIT License - see LICENSE file for details.
Raw data
{
"_id": null,
"home_page": null,
"name": "cubeparser-mcp",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.10",
"maintainer_email": null,
"keywords": "api, cubeparser, document-extraction, mcp",
"author": null,
"author_email": "CubeParser MCP <support@example.com>",
"download_url": "https://files.pythonhosted.org/packages/e6/5c/0c740cf7124e28a76fde5afcb08d9305efa372f2cfe9806a3ed6ab5d0504/cubeparser_mcp-0.1.1.tar.gz",
"platform": null,
"description": "# CubeParser MCP Server\n\nA Model Context Protocol (MCP) server that provides access to CubeParser document extraction API. This server can be run directly using `uvx` with absolute paths for easy deployment and sharing.\n\n## \ud83d\ude80 Quick Start with uvx\n\n### For End Users (Running the Server)\n\nIf someone has shared this project with you, you can run it directly using uvx with the absolute path:\n\n```bash\n# Replace with the actual absolute path provided to you\nuvx --from \"C:\\path\\to\\cubeparser_mcp\" cubeparser-mcp\n```\n\n**Example:**\n```bash\nuvx --from \"C:\\Users\\Remy\\sensedeal\\code\\projects\\work\\CITICS2025\\zhangkai\\cubeparser_mcp\" cubeparser-mcp\n```\n\n### For Developers (Setting Up for Sharing)\n\n1. **Clone and Setup**:\n```bash\ngit clone <repository-url>\ncd cubeparser_mcp\nuv sync\n```\n\n2. **Run Setup Script**:\n```bash\nuv run python setup_uvx.py\n```\n\nThis creates:\n- `mcp_config.json` - MCP client configuration with absolute paths\n- `.env.template` - Environment variables template\n- `run_cubeparser_mcp.bat` - Quick run script for Windows\n\n3. **Configure Environment**:\n```bash\ncp .env.template .env\n# Edit .env with your CubeParser credentials\n```\n\n## \ud83d\udccb Features\n\nThis MCP server provides three main tools:\n\n1. **get_templates** - Retrieve available extraction templates from CubeParser\n2. **create_task** - Upload files and create extraction tasks with specified templates\n3. **download_results** - Get extraction results from completed tasks\n\n## \ud83d\udee0\ufe0f Installation Methods\n\n### Method 1: Direct uvx Usage (Recommended for Sharing)\n\n```bash\n# Run from absolute path (replace with actual path)\nuvx --from \"/absolute/path/to/cubeparser_mcp\" cubeparser-mcp\n\n# Or on Windows\nuvx --from \"C:\\absolute\\path\\to\\cubeparser_mcp\" cubeparser-mcp\n```\n\n### Method 2: Local Development\n\n```bash\n# Install dependencies\nuv sync\n\n# Run directly\nuv run python main.py\n\n# Or use the generated batch file\n.\\run_cubeparser_mcp.bat # Windows\n./run_cubeparser_mcp.sh # Linux/Mac\n```\n\n## \u2699\ufe0f Configuration\n\n### Environment Variables\n\nCreate a `.env` file with your CubeParser credentials:\n\n```env\nCUBEPARSER_USERNAME=your_username_here\nCUBEPARSER_PASSWORD=your_password_here\nCUBEPARSER_BASEURL=https://cubeparser.cn/\n```\n\n### MCP Client Configuration\n\nUse the generated `mcp_config.json` file in your MCP client (e.g., Claude Desktop):\n\n```json\n{\n \"mcpServers\": {\n \"cubeparser\": {\n \"command\": \"uvx\",\n \"args\": [\n \"--from\",\n \"C:\\\\absolute\\\\path\\\\to\\\\cubeparser_mcp\",\n \"cubeparser-mcp\"\n ],\n \"env\": {\n \"CUBEPARSER_USERNAME\": \"your_username\",\n \"CUBEPARSER_PASSWORD\": \"your_password\",\n \"CUBEPARSER_BASEURL\": \"https://cubeparser.cn/\"\n }\n }\n }\n}\n```\n\n## \ud83d\udd27 Available Tools\n\n### get_templates()\n\nRetrieves a list of available extraction templates from CubeParser.\n\n**Returns:** List of template objects with IDs, names, and descriptions.\n\n### create_task(file_path: str, template_id: str)\n\nCreates an extraction task by uploading a file and specifying a template.\n\n**Parameters:**\n- `file_path`: Absolute path to the file to be processed\n- `template_id`: ID of the template to use for extraction\n\n**Returns:** Task information including task ID and status.\n\n### download_results(task_id: str)\n\nDownloads extraction results for a completed task.\n\n**Parameters:**\n- `task_id`: ID of the extraction task\n\n**Returns:** Extraction results and task status information.\n\n## \ud83e\uddea Testing\n\n### Test the Installation\n\n```bash\n# Test that the server starts correctly\nuvx --from \"C:\\your\\absolute\\path\\to\\cubeparser_mcp\" cubeparser-mcp\n\n# Or use the batch file\n.\\run_cubeparser_mcp.bat\n```\n\n### Run Tests\n\n```bash\nuv run pytest\n```\n\n## \ud83d\udcc1 Generated Files\n\nAfter running `setup_uvx.py`, you'll have:\n\n- **`mcp_config.json`** - Ready-to-use MCP client configuration\n- **`.env.template`** - Template for environment variables\n- **`run_cubeparser_mcp.bat`** - Windows batch script for easy testing\n- **`run_cubeparser_mcp.sh`** - Linux/Mac shell script for easy testing\n\n## \ud83d\udea8 Troubleshooting\n\n### Common Issues\n\n1. **Server won't start**: Check that environment variables are set correctly\n2. **uvx command not found**: Install uv first: `pip install uv`\n3. **Permission errors**: Ensure the absolute path is accessible\n4. **Network errors**: Verify CubeParser API credentials and network access\n\n### Debug Mode\n\nRun with verbose logging:\n\n```bash\nuvx --from \"C:\\your\\path\\to\\cubeparser_mcp\" cubeparser-mcp --verbose\n```\n\n## \ud83d\udce4 Sharing with Others\n\nTo share this MCP server with others:\n\n1. **Provide the absolute path** to your project directory\n2. **Share the uvx command**:\n ```bash\n uvx --from \"C:\\your\\absolute\\path\\to\\cubeparser_mcp\" cubeparser-mcp\n ```\n3. **Include environment setup instructions** (they need their own CubeParser credentials)\n\n## \ud83d\udcc4 License\n\nMIT License - see LICENSE file for details.\n",
"bugtrack_url": null,
"license": "MIT",
"summary": "MCP Server for CubeParser document extraction API",
"version": "0.1.1",
"project_urls": {
"Homepage": "https://github.com/your-org/cubeparser-mcp",
"Issues": "https://github.com/your-org/cubeparser-mcp/issues",
"Repository": "https://github.com/your-org/cubeparser-mcp"
},
"split_keywords": [
"api",
" cubeparser",
" document-extraction",
" mcp"
],
"urls": [
{
"comment_text": null,
"digests": {
"blake2b_256": "b03f2806db908177878fa8e8e723b818fc10b01b27268d42b2ed22689ac1423a",
"md5": "ddbe91f7f2d23a5d5f79337191371583",
"sha256": "e45a967e19704920ceba9f9cecb5cd4926aaad617bc1bd6fcea5b27f1006f71b"
},
"downloads": -1,
"filename": "cubeparser_mcp-0.1.1-py3-none-any.whl",
"has_sig": false,
"md5_digest": "ddbe91f7f2d23a5d5f79337191371583",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.10",
"size": 8112,
"upload_time": "2025-08-30T05:28:11",
"upload_time_iso_8601": "2025-08-30T05:28:11.804933Z",
"url": "https://files.pythonhosted.org/packages/b0/3f/2806db908177878fa8e8e723b818fc10b01b27268d42b2ed22689ac1423a/cubeparser_mcp-0.1.1-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": null,
"digests": {
"blake2b_256": "e65c0c740cf7124e28a76fde5afcb08d9305efa372f2cfe9806a3ed6ab5d0504",
"md5": "d59ac0eb0e374746ca210ff458e2f347",
"sha256": "dfe9946b67932e8c19e053df791394e4630c83e2d29b4bf292fb82b919e57c7a"
},
"downloads": -1,
"filename": "cubeparser_mcp-0.1.1.tar.gz",
"has_sig": false,
"md5_digest": "d59ac0eb0e374746ca210ff458e2f347",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.10",
"size": 7062,
"upload_time": "2025-08-30T05:28:13",
"upload_time_iso_8601": "2025-08-30T05:28:13.309744Z",
"url": "https://files.pythonhosted.org/packages/e6/5c/0c740cf7124e28a76fde5afcb08d9305efa372f2cfe9806a3ed6ab5d0504/cubeparser_mcp-0.1.1.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-08-30 05:28:13",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "your-org",
"github_project": "cubeparser-mcp",
"github_not_found": true,
"lcname": "cubeparser-mcp"
}
JSON
