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 |
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.