token-ninja routes deterministic shell commands locally — zero LLM calls, ~19µs latency. Works silently inside AI tools via MCP.
Quick Install
Copy the config for your editor. Some servers may need additional setup — check the README.
Add to claude_desktop_config.json:
{
"mcpServers": {
"token-ninja": {
"command": "npx",
"args": [
"-y",
"oanhduong/token-ninja"
]
}
}
}
Run in terminal:
claude mcp add token-ninja npx -y oanhduong/token-ninja
Add to .cursor/mcp.json:
{
"mcpServers": {
"token-ninja": {
"command": "npx",
"args": [
"-y",
"oanhduong/token-ninja"
]
}
}
}