I craft unique cereal names, stories, and ridiculously cute Cereal Baby images.

voxta-mcp
Voxta provider that enables communication with Model Context Protocol (MCP) servers
3 years
Works with Finder
1
Github Watches
1
Github Forks
0
Github Stars
Voxta MCP Bridge Provider
A Voxta provider that enables communication with Model Context Protocol (MCP) servers, allowing Voxta to leverage external tools and resources through the MCP protocol.
Prerequisites
- .NET 8.0 SDK
- Python 3.10 or higher
- Git
Setup Instructions
Windows
-
Clone the repository:
git clone https://github.com/voxta/voxta-mcp.git cd voxta-mcp
-
Create Python virtual environment:
python -m venv venv .\venv\Scripts\activate pip install mcp-agent
-
Build and run the project:
dotnet build dotnet run
Linux
-
Clone the repository:
git clone https://github.com/voxta/voxta-mcp.git cd voxta-mcp
-
Create Python virtual environment:
python3 -m venv venv source venv/bin/activate pip install mcp-agent
-
Build and run the project:
dotnet build dotnet run
Running the Provider
-
Ensure your MCP server is running and accessible at the configured address.
-
Configure
appsettings.json
with your settings:{ "MCPBridge": { "PythonExePath": "venv/bin/python", // Path to Python in virtual environment "MCPClientScriptPath": "mcp_client.py", // Path to the MCP client script "MCPServerAddress": "localhost:50051" // Your MCP server address } }
-
Run the provider:
dotnet run
-
The provider will:
- Start the Python MCP client process
- Connect to your MCP server
- Register with Voxta
- Begin handling action requests
-
Monitor the console output for:
- Connection status
- Action triggers
- Error messages
- MCP tool responses
Troubleshooting
Common issues and solutions:
-
"MCPClientScriptPath is not configured"
- Ensure
appsettings.json
exists and has the correct path tomcp_client.py
- Ensure
-
Python process fails to start
- Verify Python virtual environment is activated
- Check
PythonExePath
in configuration - Ensure
mcp-agent
is installed in the virtual environment
-
Cannot connect to MCP server
- Verify the server is running
- Check
MCPServerAddress
configuration - Ensure no firewall is blocking the connection
Configuration
The provider is configured through appsettings.json
:
{
"MCPBridge": {
"PythonExePath": "venv/bin/python", // On Windows: "venv\\Scripts\\python.exe"
"MCPClientScriptPath": "mcp_client.py", // Required: Path to the Python MCP client script
"MCPServerAddress": "localhost:50051" // Address of your MCP server
},
"Serilog": {
"Using": ["Serilog.Sinks.Console"],
"WriteTo": [
{
"Name": "Console",
"Args": {
"outputTemplate": "[{Timestamp:HH:mm:ss} {Level:u3}] {Message:l}{NewLine}{Exception}",
"theme": "Serilog.Sinks.SystemConsole.Themes.SystemConsoleTheme::Literate, Serilog.Sinks.Console"
}
}
],
"MinimumLevel": {
"Default": "Information",
"Override": {
"Microsoft": "Warning",
"System.Net.Http.HttpClient": "Warning",
"Voxta": "Information",
"Voxta.MCPBridgeProvider": "Debug"
}
}
}
}
Required Configuration
-
MCPBridge:MCPClientScriptPath
: Path to the Python MCP client script that handles communication with the MCP server. -
MCPBridge:MCPServerAddress
: Address of your MCP server (e.g., "localhost:50051" for a local server).
Optional Configuration
-
MCPBridge:PythonExePath
: Path to the Python executable. Defaults to "python" (or "python3" on Linux).
Connecting to MCP Servers
-
Start your MCP server (e.g., Home Assistant MCP server) and note its address (typically
localhost:50051
). -
Update the
MCPServerAddress
inappsettings.json
to match your MCP server's address. -
The provider will automatically connect to the MCP server when started and make its tools available to Voxta.
Usage
-
The provider will automatically register available MCP tools with Voxta.
-
When Voxta triggers an action, the provider will:
- Translate the Voxta action to an MCP tool call
- Send the request to the MCP server through the Python client
- Receive the response and send it back to Voxta
Development
- The C# code handles the Voxta integration and process management
- The Python script (
mcp_client.py
) handles MCP protocol communication - Both components communicate through stdin/stdout using JSON messages
License
[License information here]
相关推荐
Evaluator for marketplace product descriptions, checks for relevancy and keyword stuffing.
Confidential guide on numerology and astrology, based of GG33 Public information
A geek-themed horoscope generator blending Bitcoin prices, tech jargon, and astrological whimsy.
Converts Figma frames into front-end code for various mobile frameworks.
Advanced software engineer GPT that excels through nailing the basics.
Discover the most comprehensive and up-to-date collection of MCP servers in the market. This repository serves as a centralized hub, offering an extensive catalog of open-source and proprietary MCP servers, complete with features, documentation links, and contributors.
Micropython I2C-based manipulation of the MCP series GPIO expander, derived from Adafruit_MCP230xx
A unified API gateway for integrating multiple etherscan-like blockchain explorer APIs with Model Context Protocol (MCP) support for AI assistants.
Mirror ofhttps://github.com/agentience/practices_mcp_server
Mirror ofhttps://github.com/bitrefill/bitrefill-mcp-server
Reviews

user_H4F7JFav
Node Omnibus MCP Server by MCP-Mirror is a robust and versatile server solution. I've been using it for my applications and the performance is exceptional. The setup process is straightforward, and the server handles multiple node processes seamlessly. It's a reliable tool for anyone looking to manage node applications efficiently. Highly recommend checking it out at https://mcp.so/server/bsmi021_mcp-node-omnibus-server/MCP-Mirror.