What it does
The publisher describes this MCP server as a way to compress prompts by 40-60% using a local LLM, with embedding validation. It states that all conditionals in the prompt are preserved. The source provides no further details on usage, setup or supported clients.
Safety
Our team has not reviewed this resource. Only automated rules checked it; resources with high-risk signals are not published. These are signals, not a guarantee that installing it is safe. Try it in a sandbox project first.
- Runs code or changes an assistant's behaviour
Sources
- Official MCP Registry first seen 13 Nov 2026 · last seen 13 Nov 2026 · its page on the source
io.github.base76-research-lab/token-compressor
Compress prompts 40-60% using local LLM + embedding validation. Preserves all conditionals.
v0.1.1As shown on registry.modelcontextprotocol.io when we last read it