AI BriefingClaude context reduced by 40%
Key point
compressmcp compresses JSON keys in MCP responses to cut Claude context usage by 40%.
Details
compressmcp attaches to Claude Code's PostToolUse pipeline and compresses the JSON keys of MCP tool responses using a shared dictionary. It explains that repeated field names like transactionId, orderStatus, and repositoryDescription are abbreviated, reducing token usage while preserving the readable structure.
It claims an average 40% token reduction, and states that the original structure can be losslessly restored as long as the dictionary is available.
- Once Claude Code is restarted, it is automatically applied to all MCP tool responses.
- The status bar shows context usage, tokens saved, compression efficiency, and plan utilization.
- It highlights 262 tests and 0 cases of data loss.
- It is introduced as working with all MCP tools.
This summary was generated automatically by AI. Check the original for the author's claims and context. Copyright belongs to the original author.
Our guide explains how the AI works. Report summary errors, attribution issues, or removal requests via Contact.
Related
Claude Code Update: Memory Warnings, MCP Timeout Controls, and Stability ImprovementsForemerge v0.5.0 Released: Rust-Based Open-Source Tool Detects Intent Conflicts Between Parallel AI Coding Agents