Token Optimizer runs on your own machine — the client starts it, so there is no endpoint to ping. 36 installs a week from pypi. Last commit 20 Jul 2026.
Reversible context compression for AI agents: cut token usage up to 94%, originals retrievable
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add token_optimizer -- uvx slimctx
{
"mcpServers": {
"token_optimizer": {
"args": [
"slimctx"
],
"command": "uvx"
}
}
}
[mcp_servers.token_optimizer]
command = "uvx"
args = ["slimctx"]
{
"mcpServers": {
"token_optimizer": {
"args": [
"slimctx"
],
"command": "uvx"
}
}
}
{
"mcpServers": {
"token_optimizer": {
"args": [
"slimctx"
],
"command": "uvx"
}
}
}
Answers built from our own checks of this server.