> A token-saving MCP proxy for OpenClaw users. Cuts tool call payloads by 90%+ via lazy expansion. Why MCP tool calls often return thousands of tokens of HTML or JSON in a single response — but the model typically uses only 5% of it. The remaining 95% silently burns context window and increases cost. claw-tsaver sits between OpenClaw and your downstream MCP servers, intercepts oversized responses, and hands the model a compact preview + an on-demand handle instead. How Real measurement | Test | Original tokens | Returned tokens | Saved | |---|---|---|---| | fetch Wikipedia "Tokenization (data security)" | 11,507 | 104 | **99.1%** | Tested on OpenClaw + Claude Sonnet 4.6 + mcp-server-fetch, 2026-04-25. Raw data: benchmarks/mvp-day1-fetch.jsonl. Quick Start 1. Prerequisites Install uv (one-time setup): No claw-tsaver install needed — uvx will fetch and run it on demand. 2. Configure downstream MCP servers Edit ~/.claw-tsaver/config.json (first run of claw-tsaver-mcp will auto-create a template): 3. Register with OpenClaw Add this block at the top level of ~/.openclaw/openclaw.json: Then restart OpenClaw gateway: openclaw gateway restart Dashboard Optional: a local web UI for real-time token savings stats. Open in your browser. Roadmap - [x] **Module A**: lazy expansion proxy (this release) - [x] **Module D**: local dashboard (this release) - [ ] **Module B**: tool routing (auto-load only relevant MCPs per turn) - [ ] **Module C**: conversation history compression (atomic fact cards) License MIT — see LICENSE file. Contributing Issues and PRs welcome. --- 🇨🇳 中文说明 什么是 claw-tsaver? **claw-tsaver** 是一个为 OpenClaw 用户设计的 MCP 代理,通过懒加载扩展机制将工具调用的 token 消耗削减 **90%+**。 问题背景 MCP 工具调用(如 fetch、puppeteer)经常在单次响应中返回数千个 token 的 HTML 或 JSON,但模型通常只使用其中约 5% 的内容。剩余 95% 悄悄消耗上下文窗口并增加费用。 解决方案 claw-tsaver 作为 OpenClaw 与下游 MCP 服务器之间的代理: 1. 拦截过大的响应(超过可配置的 token 阈值)