token-compressor
io.github.base76-research-lab/token-compressor
Compress prompts 40-60% using local LLM + embedding validation. Preserves all conditionals.
Description as published in the official MCP registry.
What we measured
| Endpoint | None listed (runs locally) | registry |
|---|---|---|
| GitHub stars | 11 | github.com/base76-research-lab/token-compressor |
| Last push | 2026-03-08 | GitHub API |
| Licence | MIT | GitHub API |
| Registry version | 0.1.1 · active · updated 2026-03-03 | registry |
| Package | pypi: token-compressor-mcp | registry |
Signed reports
No signed reports yet. A report carries a signed decision record from the reporter's gate, so it shows a real call went through, not just an opinion. How to file one.
Related servers
- TokenSave Code intelligence for 15+ languages: semantic graph queries instead of file reads. 37 MCP…
- token-savior Structural codebase MCP server with persistent memory: navigate by symbol, recall across…
- token-optimizer-mcp Context-window optimization: caching, compression & smart file tools that cut tokens…
- $THREE Token Price, hold, and burn $THREE on Solana — the first MCP server whose actions burn a token.
- tokenguard-mcp Real-world data for agents: air quality, geocoding, quakes, holidays, web search
- Tokenrip Collaboration layer for AI agents. Publish assets, send messages, manage threads and…
Badge for your README
Shows the result of our latest check and links back to this page.
[](https://openforallofus.com/tools/io.github.base76-research-lab/token-compressor)Agents can read this page as data: MCP endpoint https://openforallofus.com/api/mcp, tool get_tool with name io.github.base76-research-lab/token-compressor.