Build, test and publish agentic workflows from your AI client: approve steps, read tables, see runs.
Setup
Choose your client, copy the config, then fill in any required environment variables.
claude mcp add --transport http neonloops https://app.neonloops.com/api/mcp/v1~/.codex/config.toml
[mcp_servers.neonloops]
url = "https://app.neonloops.com/api/mcp/v1"
# codex mcp add neonloops --url https://app.neonloops.com/api/mcp/v1~/.cursor/mcp.json
{
"mcpServers": {
"neonloops": {
"url": "https://app.neonloops.com/api/mcp/v1"
}
}
}.vscode/mcp.json
{
"servers": {
"neonloops": {
"type": "http",
"url": "https://app.neonloops.com/api/mcp/v1"
}
}
}~/.gemini/settings.json
{
"mcpServers": {
"neonloops": {
"httpUrl": "https://app.neonloops.com/api/mcp/v1"
}
}
}claude_desktop_config.json · Customize › Connectors › Add custom connector
{
"mcpServers": {
"neonloops": {
"command": "npx",
"args": [
"-y",
"mcp-remote",
"https://app.neonloops.com/api/mcp/v1"
]
}
}
}.trae/mcp.json
{
"mcpServers": {
"neonloops": {
"url": "https://app.neonloops.com/api/mcp/v1"
}
}
}