An MCP server that scaffolds runnable typescript MCP servers from API definitions so APIs without MCP strategy can become discoverable to AI models
Setup
Choose your client, copy the config, then fill in any required environment variables.
claude mcp add api-translator -- npx -y mcp-api-translator~/.codex/config.toml
[mcp_servers.api-translator]
command = "npx"
args = ["-y", "mcp-api-translator"]
# codex mcp add api-translator -- npx -y mcp-api-translator~/.cursor/mcp.json
{
"mcpServers": {
"api-translator": {
"command": "npx",
"args": [
"-y",
"mcp-api-translator"
]
}
}
}.vscode/mcp.json
{
"servers": {
"api-translator": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"mcp-api-translator"
]
}
}
}~/.gemini/settings.json
{
"mcpServers": {
"api-translator": {
"command": "npx",
"args": [
"-y",
"mcp-api-translator"
]
}
}
}claude_desktop_config.json
{
"mcpServers": {
"api-translator": {
"command": "npx",
"args": [
"-y",
"mcp-api-translator"
]
}
}
}.trae/mcp.json
{
"mcpServers": {
"api-translator": {
"command": "npx",
"args": [
"-y",
"mcp-api-translator"
]
}
}
}