# prompt-caching

> An open-source MCP plugin that automatically places prompt cache breakpoints for Claude API calls, reducing token costs by up to 90% on repeated turns.

prompt-caching is an open-source MCP plugin built for Claude Code and any MCP-compatible client that automatically detects stable content — system prompts, tool definitions, and file reads — and inserts Anthropic cache_control breakpoints so you pay 0.1× instead of 1× on repeated turns. It requires zero configuration and starts saving on the very next turn after install. The plugin ships four intelligent session modes and provides observability tools like `get_cache_stats` and `analyze_cacheability` that Claude Code's built-in caching does not expose.

- **BugFix Mode** — *Detects stack traces in your messages, caches the buggy file and error context once, so every follow-up only pays for the new question.*
- **Refactor Mode** — *Detects refactor keywords and file lists, caches the before-pattern, style guides, and type definitions, sending only per-file instructions fresh.*
- **File Tracking** — *Tracks read counts per file; on the second read it injects a cache breakpoint so all future reads cost 0.1× instead of 1×. Always on across all modes.*
- **Conversation Freeze** — *After N turns, freezes all messages before turn (N−3) as a cached prefix so only the last 3 turns are sent fresh, compounding savings over long sessions.*
- **Zero-config install for Claude Code** — *Run two `/plugin` commands inside Claude Code — no npm, no config file, no restart required.*
- **npm install path for other clients** — *Install globally via `npm install -g prompt-caching-mcp` and add a single JSON stanza to your MCP client config (Cursor, Windsurf, Zed, Continue.dev, etc.).*
- **Cache observability** — *`get_cache_stats` reports hit rate and cumulative token savings; `analyze_cacheability` dry-runs a prompt to show exactly where breakpoints land.*
- **Broad model support** — *Works with Claude Opus 4/4.1/4.5/4.6, Sonnet 3.7/4/4.5/4.6, Haiku 3/3.5/4.5, with cache lifetimes of 5 minutes (ephemeral) or 1 hour.*
- **MIT licensed** — *Fully open source with zero vendor lock-in; contributions welcome via the public GitHub repository.*

## Features
- Automatic cache breakpoint placement
- BugFix Mode
- Refactor Mode
- File Tracking
- Conversation Freeze
- get_cache_stats tool
- analyze_cacheability dry-run tool
- Zero configuration required
- Claude Code plugin marketplace support
- npm global install for MCP clients
- 90% average token cost reduction
- MIT open source license

## Integrations
Claude Code, Anthropic SDK, Cursor, Windsurf, ChatGPT, Perplexity, Zed, Continue.dev

## Platforms
CLI, API, DEVELOPER_SDK

## Pricing
Open Source

## Links
- Website: https://prompt-caching.ai
- Documentation: https://github.com/flightlesstux/prompt-caching
- Repository: https://github.com/flightlesstux/prompt-caching
- EveryDev.ai: https://www.everydev.ai/tools/prompt-caching