About mcp-proxy-server
mcp-proxy-server is an MCP proxy for projects that need to connect multiple backend MCP servers. It reads server definitions from JSON at a required configuration URL and can optionally write logs to a specified path.
Key features
- 01Connect multiple backend MCP servers
- 02Load JSON configuration from a URL
- 03Optional log file path
Use cases
- 01Route MCP client connections to configured backends
- 02Manage backend server definitions through hosted JSON configuration
MCP support
It acts as an MCP proxy, connecting clients with multiple backend MCP servers using the supplied configuration.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEmcp-proxy-server
A proxy server for Model Context Protocol (MCP) that allows connections to multiple backend MCP servers.
Getting Started
Installation
Globally
Install the package globally:
npm install -g @pyleeai/mcp-proxy-server
As a library
Install it in your project:
npm install @pyleeai/mcp-proxy-server
Usage
If installed globally:
mcp-proxy-server
Configuration
The MCP Proxy Server can be configured using environment variables.
CONFIGURATION_URL="http://example.com/configuration"
LOG_PATH=./logs/mcp-proxy-server.log
Environment Variables
- The CONFIGURATION_URL is required.
- The LOG_PATH is optional.
Configuration JSON
The CONFIGURATION_URL points to JSON that contains the configuration for the proxy server. It should have the following structure:
{
"mcp": {
"servers": {
"fetch": {
"args": [
"mcp-server-fetch"
],
"command": "uvx"
},
"filesystem": {
"args": [
"-y",
"@modelcontextprotocol/server-filesystem",
"."
],
"command": "npx"
}
}
}
}
Contributing
Contributions are welcome! Here's how you can contribute to the project:
Prerequisites
- Bun v1.2.2 or later
Setup
- Clone the repository:
git clone https://github.com/your-username/mcp-proxy-server.git
cd mcp-proxy-server
- Install dependencies:
bun install
Usage
Running the Server
Start the server:
bun start
Scripts
The project includes several npm scripts to help with development:
bun lint- Lints the codebase using Biomebun format- Formats the codebase using Biomebun check- Runs both lint and format checksbun typecheck- Checks TypeScript types without emitting outputbun test- Runs all testsbun start- Starts the development serverbun build- Builds the projectbun inspector- Runs the MCP inspector tool
Code Style
This project uses Biome for code formatting and linting. Please ensure your code follows these standards by running:
bun check
Testing
The project uses Bun's built-in test runner for comprehensive testing.
Running Tests
# Run all tests
bun test
# Run tests with watch mode (auto-rerun on file changes)
bun test --watch
# Run tests with coverage reporting
bun test --coverage
Test Structure
The test suite is organized in the test directory with the following subdirectories:
test/unit- Unit tests for individual componentstest/integration- Integration tests for combined components
Publishing
To publish the package to npm using Bun:
- Update the version in
package.json:
bun run npm version [patch|minor|major]
- Build the package:
bun run build
- Publish to npm:
bun publish
Note that publishing requires appropriate npm credentials and access rights.
Release Process
This project uses GoReleaser for creating and publishing releases.
GoReleaser Configuration
The release process is defined in .goreleaser.yaml and includes:
- Building for multiple platforms (Linux, macOS, Windows)
- Support for both x64 and arm64 architectures
- Creating distributable archives
- Generating changelogs
- Creating GitHub releases
Creating a Release
- Tag a new version:
git tag -a v1.0.0 -m "Release v1.0.0"
- Push the tag:
git push origin v1.0.0
- The CI/CD pipeline will automatically:
- Build for all target platforms
- Create archives for distribution
- Generate changelogs
- Publish the release on GitHub
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.