Skip to main content

A MCP Forward Proxy Bridge designed to be a one-to-many bridge allowing you to use a single MCP server to communicate with many MCP servers transparently.

Project description

MCP Foxxy Bridge

CI/CD Pipeline Release PyPI version Python 3.11+ License: AGPL v3

A MCP Forward Proxy Bridge designed to be a one-to-many bridge that allows you to use a single MCP server to communicate with many MCP servers transparently.

Overview

The MCP Foxxy Bridge solves the problem of having to configure multiple MCP servers across different AI tools by providing a centralized proxy that:

  • Aggregates multiple MCP servers into a single interface
  • Exposes all tools, resources, and prompts from configured MCP servers
  • Routes requests transparently to the appropriate underlying MCP server
  • Allows you to configure your MCPs in one place for use across all AI tools

Quick Start

Installation

Recommended: Install via uv

uv tool install mcp-foxxy-bridge

Alternative: Install via pipx

pipx install mcp-foxxy-bridge

Install latest from git

uv tool install git+https://github.com/billyjbryant/mcp-foxxy-bridge

Basic Usage

Start bridge with multiple servers:

mcp-foxxy-bridge --port 8080 \
  --named-server fetch 'uvx mcp-server-fetch' \
  --named-server github 'npx -y @modelcontextprotocol/server-github' \
  --named-server filesystem 'npx -y @modelcontextprotocol/server-filesystem'

Start bridge with configuration file:

mcp-foxxy-bridge --port 8080 --named-server-config ./servers.json

Connect AI tools to the bridge: Your bridge will be available at http://localhost:8080/sse

Claude Desktop Configuration

Add this to your Claude Desktop MCP configuration:

{
  "mcpServers": {
    "foxxy-bridge": {
      "command": "mcp-foxxy-bridge",
      "args": ["http://localhost:8080/sse"]
    }
  }
}

Architecture

AI Tools (Claude Desktop, VS Code, etc.)
    ↓ (SSE/stdio)
MCP Foxxy Bridge
    ↓ (stdio to multiple servers)
MCP Server 1, MCP Server 2, MCP Server N

The Foxxy Bridge acts as a transparent forward proxy between AI tools and multiple MCP servers, providing:

  • Tool Aggregation: Unified access to tools from all connected servers
  • Resource Aggregation: Access to resources across multiple servers
  • Namespace Management: Automatic tool/resource namespacing to prevent conflicts
  • Request Routing: Intelligent routing of requests to appropriate servers
  • Health Monitoring: Built-in status endpoint for monitoring server health

Key Features

  • One-to-Many Bridge: Connect multiple MCP servers through a single endpoint
  • Tool Aggregation: Unified access to tools from all connected servers
  • Resource Subscription: Full support for resource subscriptions and forwarding
  • Logging Coordination: Centralized logging level management across all servers
  • Progress Notifications: Transparent progress forwarding from managed servers
  • Completion Aggregation: Combined autocomplete suggestions from all servers
  • Namespace Management: Automatic tool namespacing to prevent conflicts
  • Environment Variables: Support for ${VAR_NAME} expansion in configs
  • Multiple Deployment Options: Local process, Docker container, or UV tool
  • Health Monitoring: Built-in status endpoint for monitoring

Documentation

📚 Complete Documentation

Development

Requirements

  • Python 3.11+
  • uv package manager
  • Node.js (for MCP servers that require it)

Development Setup

# Clone the repository
git clone https://github.com/billyjbryant/mcp-foxxy-bridge.git
cd mcp-foxxy-bridge

# Install dependencies
uv sync --dev

# Run tests
uv run pytest

# Run linting
uv run ruff check

# Run type checking
uv run mypy src/

# Run the bridge in development
uv run -m mcp_foxxy_bridge --port 8080

Docker Development

# Build Docker image
docker build -t mcp-foxxy-bridge .

# Run with Docker
docker run --rm -p 8080:8080 mcp-foxxy-bridge

Contributing

We welcome contributions! Please see our Contributing Guide for details on:

  • Development setup
  • Code style and linting
  • Testing requirements
  • Pull request process

License

This project is licensed under the GNU Affero General Public License v3.0 or later (AGPLv3+). See the LICENSE file for details.

Support


MCP Foxxy Bridge - Bridging the gap between AI tools and multiple MCP servers.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

mcp_foxxy_bridge-1.0.0.tar.gz (153.5 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

mcp_foxxy_bridge-1.0.0-py3-none-any.whl (36.9 kB view details)

Uploaded Python 3

File details

Details for the file mcp_foxxy_bridge-1.0.0.tar.gz.

File metadata

  • Download URL: mcp_foxxy_bridge-1.0.0.tar.gz
  • Upload date:
  • Size: 153.5 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.12.9

File hashes

Hashes for mcp_foxxy_bridge-1.0.0.tar.gz
Algorithm Hash digest
SHA256 a432d5836247110c7ea7ab8ab1c2c61dba22da09569cc59ea7b43021f2db721b
MD5 d058013b39802052f00e0eed4f6537c2
BLAKE2b-256 db04f132f9a98c2d0bee552fce84e4efee46ee028b8ead6e0bcb09a9afed4c9b

See more details on using hashes here.

Provenance

The following attestation bundles were made for mcp_foxxy_bridge-1.0.0.tar.gz:

Publisher: main.yml on billyjbryant/mcp-foxxy-bridge

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file mcp_foxxy_bridge-1.0.0-py3-none-any.whl.

File metadata

File hashes

Hashes for mcp_foxxy_bridge-1.0.0-py3-none-any.whl
Algorithm Hash digest
SHA256 50d48781f813d73daa67152fc3142d1ff68d7c2b64427d1daa47c0f59b91e432
MD5 a945d54ac6f9ed2713981cc485e537eb
BLAKE2b-256 7367128f7f65cb979798779a4e04831fb364dc0e5165cae0da545c65201a0658

See more details on using hashes here.

Provenance

The following attestation bundles were made for mcp_foxxy_bridge-1.0.0-py3-none-any.whl:

Publisher: main.yml on billyjbryant/mcp-foxxy-bridge

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page