# token-compressor MCP server

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

## Links
- Registry page: https://www.getdrio.com/mcp/io-github-base76-research-lab-token-compressor
- Repository: https://github.com/base76-research-lab/token-compressor

## Install
- Command: `uvx token-compressor-mcp`
- Auth: Not captured

## Setup notes
- Package: Pypi token-compressor-mcp v0.1.1

## Tools
Not captured

## Resources
Not captured

## Prompts
Not captured

## Metadata
- Owner: io.github.base76-research-lab
- Version: 0.1.1
- Runtime: Pypi
- Transports: STDIO
- License: Not captured
- Language: Not captured
- Stars: Not captured
- Updated: Mar 3, 2026
- Source: https://registry.modelcontextprotocol.io