context-mode

Context Mode

The other half of the context problem.

Every MCP tool call in Claude Code dumps raw data into your 200K context window. A Playwright snapshot costs 56 KB. Twenty GitHub issues cost 59 KB. One access log — 45 KB. After 30 minutes, 40% of your context is gone.

Inspired by Cloudflare's Code Mode — which compresses tool definitions from millions of tokens into ~1,000 — we asked: what about the other direction?

Context Mode is an MCP server that sits between Claude Code and these outputs. 315 KB becomes 5.4 KB. 98% reduction.

https://github.com/user-attachments/assets/07013dbf-07c0-4ef1-974a-33ea1207637b

Install

/plugin marketplace add mksglu/claude-context-mode
/plugin install context-mode@claude-context-mode

Restart Claude Code. Done. This installs the MCP server + a PreToolUse hook that automatically routes tool outputs through the sandbox + slash commands for diagnostics and upgrades.

claude mcp add context-mode -- npx -y context-mode

claude --plugin-dir ./path/to/context-mode

The Problem

MCP has become the standard way for AI agents to use external tools. But there is a tension at its core: every tool interaction fills the context window from both sides — definitions on the way in, raw output on the way out.

With 81+ tools active, 143K tokens (72%) get consumed before your first message. And then the tools start returning data. A single Playwright snapshot burns 56 KB. A gh issue list dumps 59 KB. Run a test suite, read a log file, fetch documentation — each response eats into what remains.

Code Mode showed that tool definitions can be compressed by 99.9%. Context Mode applies the same principle to tool outputs — processing them in sandboxes so only summaries reach the model.

Tools

How the Sandbox Works

Each execute call spawns an isolated subprocess with its own process boundary. Scripts can't access each other's memory or state. The subprocess runs your code, captures stdout, and only that stdout enters the conversation context. The raw data — log files, API responses, snapshots — never leaves the sandbox.

Eleven language runtimes are available: JavaScript, TypeScript, Python, Shell, Ruby, Go, Rust, PHP, Perl, R, and Elixir. Bun is auto-detected for 3-5x faster JS/TS execution.

Authenticated CLIs work through credential passthrough — gh, aws, gcloud, kubectl, docker inherit environment variables and config paths without exposing them to the conversation.

When output exceeds 5 KB and an intent is provided, Context Mode switches to intent-driven filtering: it indexes the full output into the knowledge base, searches for sections matching your intent, and returns only the relevant matches with a vocabulary of searchable terms for follow-up queries.

How the Knowledge Base Works