The harness between AI agents and your cloud. Your agent gets a branch of your live AWS, tries changes, and gets a two sided diff and a pass/warn/block verdict from security, dependency, cost and limits lenses, before anything touches production. Read only. Open source.
Setup
Choose your client, copy the config, then fill in any required environment variables.
claude mcp add emfirge -- npx -y @emfirge/mcp~/.codex/config.toml
[mcp_servers.emfirge]
command = "npx"
args = ["-y", "@emfirge/mcp"]
# codex mcp add emfirge -- npx -y @emfirge/mcp~/.cursor/mcp.json
{
"mcpServers": {
"emfirge": {
"command": "npx",
"args": [
"-y",
"@emfirge/mcp"
]
}
}
}.vscode/mcp.json
{
"servers": {
"emfirge": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@emfirge/mcp"
]
}
}
}~/.gemini/settings.json
{
"mcpServers": {
"emfirge": {
"command": "npx",
"args": [
"-y",
"@emfirge/mcp"
]
}
}
}claude_desktop_config.json
{
"mcpServers": {
"emfirge": {
"command": "npx",
"args": [
"-y",
"@emfirge/mcp"
]
}
}
}.trae/mcp.json
{
"mcpServers": {
"emfirge": {
"command": "npx",
"args": [
"-y",
"@emfirge/mcp"
]
}
}
}