Token Optimizer MCP

token-optimizer-mcp

Context compression and caching, token savings tracking per agent. Global npm install turns on Claude hooks and wraps commands; telemetry is off by default

  • 544 ★ on the repository
  • Last commit
  • MIT
MCP server

Extended access

Why this level

  • Global installation turns on Claude hooks and wraps commands
  • The savings claims are not verified
All reasons and checks

ooples/token-optimizer-mcp

Install

Manual install

/plugin marketplace add ooples/token-optimizer-mcp

Then /plugin install token-optimizer@token-optimizer. Diagnostics: npx token-optimizer-doctor. Global npm installation turns on Claude hooks.

Access and checks

How we review

Extended accessThe tool runs code or makes network calls and only reads external data.

  • Global installation turns on Claude hooks and wraps commands
  • The savings claims are not verified

This is third-party code. Review the repository files before installing.

What it does

Token Optimizer MCP compresses and caches context and tracks net token savings per agent. The plugin installs with `/plugin marketplace add ooples/token-optimizer-mcp` and `/plugin install token-optimizer@token-optimizer`. The `npx token-optimizer-doctor` command shows what is on. Global npm installation turns on Claude hooks and wraps commands: the README has a Managed commands section. Telemetry is off by default and turned on explicitly. Version 7.3.0 from 23.09.2026, MIT license.

Who it is for. For people who want to see how many tokens different agents spend and compress repeating context.

Good fit when

  • You need to count and cut token spend per agent
  • You need caching and context compression
  • You need diagnostics with the token-optimizer-doctor command

Not a fit when

  • You cannot change the agent's commands and hooks
  • You need verified savings figures: the author's claims are not verified

Example request

Show how many tokens agents spent in a week by project and where context repeats most often

MCP

Transport
stdio
Authentication
not required

Limitations

Global npm installation turns on Claude hooks and wraps commands, so access is extended: read the Managed commands section. Telemetry is off by default. We have not verified the savings claims in the README, so measure on your own project. The repository has stray service files, a sign of carelessness and not a threat.

How to disable. Remove the plugin through the plugin manager, the package with npm uninstall -g and the hooks it added.

FAQ

What does Token Optimizer MCP do?

It compresses and caches context and tracks token savings per agent.

Is there telemetry?

Off by default and turned on explicitly.

What does global installation do?

It turns on Claude hooks and wraps commands, details in the Managed commands section.

Discussion

No questions or reviews yet.

An MCP server that keeps large tool output out of the agent's context window and stores session memory in SQLite

MCP serverExtended access28KRepository stars

A CLI that turns any MCP server, OpenAPI spec or GraphQL endpoint into commands at runtime, with no codegen

CLIBroad access2.4KRepository stars
Official

An MCP server and web tool for improving prompts: three tools for optimizing system and user prompts with iterative refinement

MCP serverExtended access37.9KRepository stars
Official

Local context compression for agents: tool outputs, logs, files and RAG chunks shrink before reaching the LLM. Proxy, CLI, library and MCP

MCP serverBroad access75.2KRepository stars

A local context layer for coding agents: it understands the task, routes and compresses context and tracks the cost

CLIExtended access3.9KRepository stars

A universal MCP CLI client from Apify: persistent sessions, OAuth, JSON output for scripts and shell access to any MCP server for agents

CLIBroad access1KRepository stars

Comparison with similar tools

Entries that share the main search query, and how they differ.

EntryOfficialAuthenticationRepository starsMain difference
Token Optimizer MCP (this entry)nonot required544
Token Optimizerno2,548a plugin that trims wasted tokens and keeps work across sessions
cost-xrayno4,696captures local API traffic and splits tokens and cost by source
Entrolyno476reversible context compression that wraps the agent launch

README in short

The README describes an MCP server for context compression and caching with token savings tracking, a plugin and diagnostics. MIT license.

README badge

Report a problem

Foxx AIToken Optimizer MCP
Foxx AI

I am Foxx AI and I have already vetted this tool. Ask about install, setup or anything else, and I will keep it simple.