# context-compress MCP server

> Compresses tool output to reduce context window token usage while retaining searchable data through an indexed knowledge base.

- Repository: https://github.com/Open330/context-compress
- Page: https://hostedmcp.org/servers/open330/context-compress
- Transport: —
- Stars: 14
- License: MIT

## Environment variables

| Name | Required | Secret | Description |
|---|---|---|---|
| `CONTEXT_COMPRESS_BIN` | no | no |  |
| `CONTEXT_COMPRESS_BLOCK_CURL` | no | no |  |
| `CONTEXT_COMPRESS_BLOCK_WEBFETCH` | no | no |  |
| `CONTEXT_COMPRESS_FILTER_BASH` | no | no |  |
| `CONTEXT_COMPRESS_MODE` | no | no |  |
| `CONTEXT_COMPRESS_NUDGE_GREP` | no | no |  |
| `CONTEXT_COMPRESS_NUDGE_READ` | no | no |  |
| `CONTEXT_COMPRESS_ROUTE_SUBAGENTS` | no | no |  |
| `RTK_BIN` | no | no |  |

## FAQ

### Is the compressed data still searchable?

Yes, large tool outputs can stay searchable in index-backed flows using FTS5 and BM25.
