Token Optimizer MCP Server

by omkar9854 Your server? Claim it

local only

Token Optimizer runs on your own machine — the client starts it, so there is no endpoint to ping. 55 installs a week from pypi. Last commit 20 Jul 2026.

Reversible context compression for AI agents: cut token usage up to 94%, originals retrievable

Installs per day peak 15 · avg 6 · +62% w/w

a month agotoday

Installs / week

pypi · slimctx

Stars

0 open issues

20 Jul 2026

Last commit

from GitHub

Apache-2.0

License

Python

Nothing serious here today

Today is the operative word: we check Token Optimizer every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.

Connect this server

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 Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add token_optimizer -- uvx slimctx

~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "token_optimizer": {
      "command": "uvx",
      "args": [
        "slimctx"
      ]
    }
  }
}

~/.codex/config.toml

[mcp_servers.token_optimizer]
command = "uvx"
args = ["slimctx"]

.cursor/mcp.json

{
  "mcpServers": {
    "token_optimizer": {
      "command": "uvx",
      "args": [
        "slimctx"
      ]
    }
  }
}

.vscode/mcp.json

{
  "servers": {
    "token_optimizer": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "slimctx"
      ]
    }
  }
}

Alternatives to Token Optimizer

same job, measured the same way

Sarup

by phuicmt

Thai-first context compression; shrinks long Thai and English text, originals retrievable.

60 installs/wk local only

Smart Context MCP

by arrayo

Reduces AI agent token usage by 90% via context compression and task checkpoint persistence.

100 installs/wk local only

Cap Shield

by robinlidberg-dot

Context selection and compression for AI agents - recall measured, not claimed.

135 installs/wk local only

Context7

by upstash

Up-to-date docs for AI agents

741 246 installs/wk 2 tools answering

Cuemap MCP

by cuemap-dev

Local memory and context retrieval for AI agents through CueMap.

71 installs/wk local only

Sippion

by sitten-tokyo

Local read-only repository context retrieval for AI coding agents.

local only

token-gate-mcp

by abduljabbarbxr

Token and context budget for AI agents. Tracks spend and gates the session.

49 installs/wk local only

Memdata

by thelabvenice

Persistent memory for AI agents. Store context, retrieve it semantically.

50 installs/wk local only

Token Optimizer — questions

Answers built from our own checks of this server.

Why is there no uptime for Token Optimizer?

Token Optimizer runs on your own machine over stdio — there is no network address to reach, so uptime cannot be measured for it by anyone. What can be measured is adoption: the pypi package slimctx was installed 55 times last week.

How do I connect Token Optimizer?

Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It runs locally, so the command pulls slimctx straight from pypi; nothing to host, nothing to sign up for.

How many people use Token Optimizer?

The pypi package slimctx was installed 55 times in the last week. Week over week that is +62%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.

Is Token Optimizer open source?

Yes — it is published under the Apache-2.0 licence, written in Python and 1 stars on GitHub. The source link is on this page, so you can read exactly what it does with your data before you connect it.