claude mcp add igital-hreads-token-pilot -- npx -y token-pilot
{
"mcpServers": {
"igital-hreads-token-pilot": {
"command": "npx",
"args": ["-y", "token-pilot"]
}
}
}
{
"mcpServers": {
"igital-hreads-token-pilot": {
"command": "npx",
"args": ["-y", "token-pilot"]
}
}
}
{
"mcpServers": {
"igital-hreads-token-pilot": {
"command": "npx",
"args": ["-y", "token-pilot"]
}
}
}
About This MCP Server
The token-pilot server is a developer tool that enables efficient use of tokens when interacting with AI coding assistants, saving up to 80% of tokens by utilizing AST-aware structural reading. It connects to AI models via standard input/output streams, allowing for optimized communication and token usage. Developers would use token-pilot when working with AI-powered coding tools to minimize token consumption and reduce costs.
Save up to 80% tokens when AI reads code via AST-aware structural reading. This is a Model Context Protocol (MCP) server that extends AI assistants like Claude with developer tools capabilities via the stdio transport.
Package
token-pilot on npm
HOW TO USE
Select your AI client above to get the install command. This MCP server uses the stdio transport and is available on npm.
What tools does it provide?
The token-pilot server extends your AI assistant with developer tools capabilities. Once installed, your AI can use its tools automatically.
