Reduces token usage of AI coding agents through caching, compression and context optimization, and measures the savings per client.
Setup
Choose your client, copy the config, then fill in any required environment variables.
claude mcp add token-optimizer -- npx -y @ooples/token-optimizer-mcp~/.codex/config.toml
[mcp_servers.token-optimizer]
command = "npx"
args = ["-y", "@ooples/token-optimizer-mcp"]
# codex mcp add token-optimizer -- npx -y @ooples/token-optimizer-mcp~/.cursor/mcp.json
{
"mcpServers": {
"token-optimizer": {
"command": "npx",
"args": [
"-y",
"@ooples/token-optimizer-mcp"
]
}
}
}.vscode/mcp.json
{
"servers": {
"token-optimizer": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@ooples/token-optimizer-mcp"
]
}
}
}~/.gemini/settings.json
{
"mcpServers": {
"token-optimizer": {
"command": "npx",
"args": [
"-y",
"@ooples/token-optimizer-mcp"
]
}
}
}claude_desktop_config.json
{
"mcpServers": {
"token-optimizer": {
"command": "npx",
"args": [
"-y",
"@ooples/token-optimizer-mcp"
]
}
}
}.trae/mcp.json
{
"mcpServers": {
"token-optimizer": {
"command": "npx",
"args": [
"-y",
"@ooples/token-optimizer-mcp"
]
}
}
}