Save 60-80% tokens when AI reads code — MCP server for token-efficient code navigation with AST-aware structural reading
Setup
Choose your client, copy the config, then fill in any required environment variables.
claude mcp add token-pilot -- npx -y token-pilot~/.codex/config.toml
[mcp_servers.token-pilot]
command = "npx"
args = ["-y", "token-pilot"]
# codex mcp add token-pilot -- npx -y token-pilot~/.cursor/mcp.json
{
"mcpServers": {
"token-pilot": {
"command": "npx",
"args": [
"-y",
"token-pilot"
]
}
}
}.vscode/mcp.json
{
"servers": {
"token-pilot": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"token-pilot"
]
}
}
}~/.gemini/settings.json
{
"mcpServers": {
"token-pilot": {
"command": "npx",
"args": [
"-y",
"token-pilot"
]
}
}
}claude_desktop_config.json
{
"mcpServers": {
"token-pilot": {
"command": "npx",
"args": [
"-y",
"token-pilot"
]
}
}
}.trae/mcp.json
{
"mcpServers": {
"token-pilot": {
"command": "npx",
"args": [
"-y",
"token-pilot"
]
}
}
}