io.github.base76-research-lab/token-compressor

About this integration

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

Transport

stdio

Authentication

none

Initial setup

none

Runtime

unattended

Evidence

documented

Version

0.1.1

Package

token-compressor-mcp

Last compatibility test

Not independently tested

Connect your agent

Publisher README and executable manifest reviewed; package and integration endpoint were not executed or independently security-audited.

Capabilities: Compress prompts with local models, Report semantic coverage

Connected profiles

Additional details