mcp-agent-bridge
🤖 Connect AI agents seamlessly with the MCP Agent Bridge for bidirectional communication and orchestration across multiple platforms.
claude mcp add --transport stdio alyamani18-mcp-agent-bridge docker run -i alyamani18/mcp-agent-bridge
How to use
mcp-agent-bridge serves as a connectivity bridge that enables smooth communication between multiple AI agent systems, specifically enabling integration between Codex CLI, Claude CLI, Gemini CLI, and Agent Zero. Once running, you can route prompts and responses between these agents through the bridge, allowing you to orchestrate tasks that leverage the strengths of each model. The bridge focuses on providing a unified interface for agent-to-agent coordination, task delegation, and data sharing, so you can build workflows where one agent handles planning while another executes actions or fetches results.
To use the tool, start the container (or run the binary if you obtain a local build), then configure your agent endpoints and authentication details as needed. The bridge exposes a coordination surface that agents can subscribe to or publish to, enabling bidirectional communication and message routing. Use the provided UI or config files to map specific intents to the corresponding agent CLI, ensuring that prompts are directed to the most appropriate model for the task at hand.
How to install
Prerequisites:
- Docker installed and running on your system (Linux, macOS, or Windows with WSL).
- Internet access to pull the image from the registry.
Installation steps:
-
Pull the Docker image: docker pull alyamani18/mcp-agent-bridge
-
Run the container interactively to start the bridge: docker run -it --rm
-v /path/to/config:/app/config
-e BRIDGE_CONFIG=/app/config/config.yaml
alyamani18/mcp-agent-bridge -
If you prefer to run a detached container: docker run -d --name mcp-agent-bridge
-v /path/to/config:/app/config
-e BRIDGE_CONFIG=/app/config/config.yaml
alyamani18/mcp-agent-bridge -
Verify the service is up by checking logs: docker logs -f mcp-agent-bridge
-
If you have a local configuration file, place it in the mounted config path and reference it via BRIDGE_CONFIG as shown above.
Additional notes
Notes and tips:
- Environment variables: BRIDGE_CONFIG can point to a YAML/JSON configuration file that defines agent endpoints, authentication tokens, and routing rules. If your deployment uses different paths, adjust the volume mount and env variable accordingly.
- Compatibility: The bridge is designed to work with Codex CLI, Claude CLI, Gemini CLI, and Agent Zero; ensure you have the corresponding CLI tools installed and accessible from within the container if the bridge needs to invoke them directly.
- Networking: When running behind a corporate proxy or in restricted networks, ensure Docker has outbound access and that any required CLIs can reach their respective endpoints.
- Troubleshooting: If agents fail to connect, verify that the endpoints are correct, credentials are valid, and that the container has permission to reach external services. Check container logs for error messages and adjust configuration as needed.
Related MCP Servers
ai-guide
程序员鱼皮的 AI 资源大全 + Vibe Coding 零基础教程,分享大模型选择指南(DeepSeek / GPT / Gemini / Claude)、最新 AI 资讯、Prompt 提示词大全、AI 知识百科(RAG / MCP / A2A)、AI 编程教程、AI 工具用法(Cursor / Claude Code / OpenClaw / TRAE / Lovable / Agent Skills)、AI 开发框架教程(Spring AI / LangChain)、AI 产品变现指南,帮你快速掌握 AI 技术,走在时代前沿。本项目为开源文档版本,已升级为鱼皮 AI 导航网站
hexstrike-ai
HexStrike AI MCP Agents is an advanced MCP server that lets AI agents (Claude, GPT, Copilot, etc.) autonomously run 150+ cybersecurity tools for automated pentesting, vulnerability discovery, bug bounty automation, and security research. Seamlessly bridge LLMs with real-world offensive security capabilities.
cursor-talk-to-figma
TalkToFigma: MCP integration between AI Agent (Cursor, Claude Code) and Figma, allowing Agentic AI to communicate with Figma for reading designs and modifying them programmatically.
Unity
AI-powered bridge connecting LLMs and advanced AI agents to the Unity Editor via the Model Context Protocol (MCP). Chat with AI to generate code, debug errors, and automate game development tasks directly within your project.
CyberStrikeAI
CyberStrikeAI is an AI-native security testing platform built in Go. It integrates 100+ security tools, an intelligent orchestration engine, role-based testing with predefined security roles, a skills system with specialized testing skills, and comprehensive lifecycle management capabilities.
coplay-unity-plugin
Unity plugin for Coplay