SSyncDev

Token MCP Server

Compress prompts 40-60% using local LLM + embedding validation. Preserves all conditionals.

Local serverstdioPython

What is the Token MCP Server?

Compress prompts 40-60% using local LLM + embedding validation. Preserves all conditionals.

What you get

Built by Base76 Research Lab — research into epistemic AI architecture.

Configuration and credentials

  • Python 3.10+ - Ollama running locally - Two models pulled: - Python dependencies: ---

More MCP options

Compare MCP servers by category, or browse hosted MCP servers if you prefer an endpoint over a local process.

Maintainer setup documentation.

How to install the Token MCP Server

claude mcp add token-compressor -- uvx ollama

Configuration

  • Python 3.10+ - Ollama running locally - Two models pulled: - Python dependencies: ---

Frequently asked questions

Compress prompts 40-60% using local LLM + embedding validation. Preserves all conditionals. Confirm the tools offered by your installed version in the connected client. Tool availability and permissions depend on the server and account configuration.

Alternatives to the Token MCP Server

Puppeteer

Official

The original Chromium automation reference server — simple, screenshot-driven browser control.

Browser AutomationTypeScript★ 63.0k

Fonoster

Build a programmable telecommunications stack for connecting telephony services with the Internet via a cloud-based utility.

AI & ML ServicesTypeScript★ 8.1k

Agentic Developer MCP

MCP server that wraps OpenAI Codex CLI and exposes MCP API

AI & ML ServicesPython

Ytranscript-mcp

YouTube transcripts for AI tools. No proxies needed; transcribes videos without captions.

Media & Entertainment

Echo

Text-to-speech API: neural voices, pay-per-credit in Bitcoin sats via BTCPay.

AI & ML ServicesRemote

Callwright

Self-hosted MCP voice agent that places phone calls on your behalf via Retell.

AI & ML Services