A
securityA
licenseA
qualityAI assistants to query and analyze Azure Data Explorer databases through standardized interfaces.
Last updated -
4
48
MIT License
Orion Vision MCP Server 🚀
🔌 Compatible with Cline, Cursor, Claude Desktop, and any other MCP Clients!
Orion Vision MCP is also compatible with any MCP client
The Model Context Protocol (MCP) is an open standard that enables AI systems to interact seamlessly with various data sources and tools, facilitating secure, two-way connections.
The Orion Vision MCP server provides:
Seamless integration with Azure Form Recognizer / Document Intelligence
Document analysis and form data extraction capabilities
Support for various document types (receipts, invoices, ID documents, etc.)
Type-safe operations with TypeScript
Prerequisites 🔧
Before you begin, ensure you have:
Azure Form Recognizer / Document Intelligence endpoint and key
Claude Desktop or Cursor
Node.js (v20 or higher)
Git installed (only needed if using Git installation method)
Orion Vision MCP server installation ⚡
Running with NPX
npx -y orion-vision-mcp@latest
Installing via Smithery
To install Orion Vision MCP Server for Claude Desktop automatically via Smithery:
npx -y @smithery/cli install @orion-vision/mcp --client claude
Configuring MCP Clients ⚙️
Configuring Cline 🤖
The easiest way to set up the Orion Vision MCP server in Cline is through the marketplace with a single click:
Open Cline in VS Code
Click on the Cline icon in the sidebar
Navigate to the "MCP Servers" tab (4 squares)
Search "Orion Vision" and click "install"
When prompted, enter your Azure Form Recognizer credentials
Alternatively, you can manually set up the Orion Vision MCP server in Cline:
Open the Cline MCP settings file:
# For macOS:
code ~/Library/Application\ Support/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json
# For Windows:
code %APPDATA%\Code\User\globalStorage\saoudrizwan.claude-dev\settings\cline_mcp_settings.json
Add the Orion Vision server configuration to the file:
{
"mcpServers": {
"orion-vision-mcp": {
"command": "npx",
"args": ["-y", "orion-vision-mcp@latest"],
"env": {
"AZURE_FORM_RECOGNIZER_ENDPOINT": "your-endpoint-here",
"AZURE_FORM_RECOGNIZER_KEY": "your-key-here"
},
"disabled": false,
"autoApprove": []
}
}
}
Save the file and restart Cline if it's already running.
Configuring Cursor 🖥️
Note: Requires Cursor version 0.45.6 or higher
To set up the Orion Vision MCP server in Cursor:
Open Cursor Settings
Navigate to Features > MCP Servers
Click on the "+ Add New MCP Server" button
Fill out the following information:
Name: Enter a nickname for the server (e.g., "orion-vision-mcp")
Type: Select "command" as the type
Command: Enter the command to run the server:
env AZURE_FORM_RECOGNIZER_ENDPOINT=your-endpoint AZURE_FORM_RECOGNIZER_KEY=your-key npx -y orion-vision-mcp@latestImportant: Replace
your-endpointandyour-keywith your Azure Form Recognizer credentials
Configuring the Claude Desktop app 🖥️
For macOS:
# Create the config file if it doesn't exist
touch "$HOME/Library/Application Support/Claude/claude_desktop_config.json"
# Opens the config file in TextEdit
open -e "$HOME/Library/Application Support/Claude/claude_desktop_config.json"
For Windows:
code %APPDATA%\Claude\claude_desktop_config.json
Add the Orion Vision server configuration:
{
"mcpServers": {
"orion-vision-mcp": {
"command": "npx",
"args": ["-y", "orion-vision-mcp@latest"],
"env": {
"AZURE_FORM_RECOGNIZER_ENDPOINT": "your-endpoint-here",
"AZURE_FORM_RECOGNIZER_KEY": "your-key-here"
}
}
}
}
Usage in Claude Desktop App 🎯
Once the installation is complete, and the Claude desktop app is configured, you must completely close and re-open the Claude desktop app to see the orion-vision-mcp server. You should see a hammer icon in the bottom left of the app, indicating available MCP tools.
Orion Vision Examples
Analyze a Document:
Analyze the document at "https://example.com/document.pdf" using Azure Form Recognizer.
Extract Form Data:
Extract data from the invoice at "https://example.com/invoice.pdf".
Process ID Document:
Process the ID document at "https://example.com/id.pdf" and extract relevant information.
Troubleshooting 🛠️
Common Issues
Server Not Found
Verify the npm installation by running
npm --versionCheck Claude Desktop configuration syntax
Ensure Node.js is properly installed by running
node --version
Azure Form Recognizer Credentials Issues
Confirm your Azure Form Recognizer endpoint and key are valid
Check the credentials are correctly set in the config
Verify no spaces or quotes around the credentials
Document Processing Issues
Verify the document URL is accessible
Check the document format is supported
Ensure the document is not corrupted or password-protected
Acknowledgments ✨
Model Context Protocol for the MCP specification
Anthropic for Claude Desktop
Microsoft Azure for Form Recognizer / Document Intelligence
remote-capable server
The server can be hosted and run remotely because it primarily relies on remote services or has no dependency on the local environment.
Enables AI systems to analyze documents and extract form data through Azure Form Recognizer/Document Intelligence, supporting various document types including receipts, invoices, and ID documents.
Related MCP Servers
- AsecurityFlicenseAqualityEnables AI systems to perform full-text and semantic search operations over structured/unstructured data in Azure Cognitive Search, with capabilities for document indexing and management through natural language.Last updated -3253
- -securityAlicense-qualityA comprehensive server that enables AI applications to interact with Microsoft 365 and Azure AD services through standardized Model Context Protocol interfaces.Last updated -1MIT License
- -securityFlicense-qualityEnables reading and processing various document formats including Word, PDF, RTF, and text files. Supports extracting media elements like images and links, with features for PDF page range selection and automatic text encoding detection.Last updated -2