The missing integration layer for AI agents. Let them call any OpenAPI / MCP / GraphQL / custom js functions in secure environment.
Setup
Choose your client, copy the config, then fill in any required environment variables.
claude mcp add executor -- npx -y executor~/.codex/config.toml
[mcp_servers.executor]
command = "npx"
args = ["-y", "executor"]
# codex mcp add executor -- npx -y executor~/.cursor/mcp.json
{
"mcpServers": {
"executor": {
"command": "npx",
"args": [
"-y",
"executor"
]
}
}
}.vscode/mcp.json
{
"servers": {
"executor": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"executor"
]
}
}
}~/.gemini/settings.json
{
"mcpServers": {
"executor": {
"command": "npx",
"args": [
"-y",
"executor"
]
}
}
}claude_desktop_config.json
{
"mcpServers": {
"executor": {
"command": "npx",
"args": [
"-y",
"executor"
]
}
}
}.trae/mcp.json
{
"mcpServers": {
"executor": {
"command": "npx",
"args": [
"-y",
"executor"
]
}
}
}