A workstation-local event bus: your AI coding agents wait on events instead of polling — and hear each other fail.
Setup
Choose your client, copy the config, then fill in any required environment variables.
claude mcp add waitbus -- uvx waitbus~/.codex/config.toml
[mcp_servers.waitbus]
command = "uvx"
args = ["waitbus"]
# codex mcp add waitbus -- uvx waitbus~/.cursor/mcp.json
{
"mcpServers": {
"waitbus": {
"command": "uvx",
"args": [
"waitbus"
]
}
}
}.vscode/mcp.json
{
"servers": {
"waitbus": {
"type": "stdio",
"command": "uvx",
"args": [
"waitbus"
]
}
}
}~/.gemini/settings.json
{
"mcpServers": {
"waitbus": {
"command": "uvx",
"args": [
"waitbus"
]
}
}
}claude_desktop_config.json
{
"mcpServers": {
"waitbus": {
"command": "uvx",
"args": [
"waitbus"
]
}
}
}.trae/mcp.json
{
"mcpServers": {
"waitbus": {
"command": "uvx",
"args": [
"waitbus"
]
}
}
}