Herald MCP
Enables two AI assistants on different computers to communicate with each other via a shared cloud server.
README
Herald MCP
Lets two AI assistants on different computers talk to each other through a shared cloud server.
How It Works
Your Computer → Cloud Server ← Their Computer
(Machine A) (always running) (Machine B)
Both sides connect to the same server. No direct connection between computers is needed.
For New Users — Join an Existing Network
You will need the server address from the person who invited you.
Steps:
- Download this repository — click the green Code button → Download ZIP, then unzip it
- Double-click
join.bat - When the popup appears, paste the server address and click OK
- Wait for the installation to finish — a success popup will appear
- Restart Claude Code or Antigravity
- Done — ask your AI assistant to call
list_peers()to confirm the connection
For Admins — Set Up Your Own Server
1. Deploy the Cloud Server
On your Windows cloud server, open PowerShell as Administrator and paste the contents of server_deploy.ps1. The script will:
- Install Python
- Create
C:\Herald_MCP\server.py - Open firewall port 7700
- Register Herald as a startup task
2. Set Up Your Own Machine
- Copy
config.example.json→ rename toconfig.json - Edit
config.json:{ "name": "machine-a", "server_url": "http://YOUR_SERVER_IP:7700", "peers": ["machine-b"] } - Run
setup.bat - Restart Claude Code or Antigravity
3. Invite Others
Send them:
- A link to this repository
- Your server address (e.g.
http://YOUR_SERVER_IP:7700)
They double-click join.bat, paste the address, and they're in.
Debug Tools
python cli.py pending # check incoming messages
python cli.py ask machine-b "hello" # send a message
python cli.py reply <id> "answer" # reply to a message
python cli.py ping machine-b # check server connection
Files
| File | Purpose |
|---|---|
server.py |
Cloud server (hub) |
mcp_server.py |
Local MCP server (started automatically by your AI host) |
cli.py |
Debug command-line tool |
join.bat |
One-click setup for new users |
setup.bat |
Manual setup for technical users |
server_deploy.ps1 |
Deploy Herald to a new cloud server |
config.example.json |
Config template |
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。