Token Save MCP — AI skill for Claude Code

token-save-mcp

**Your coding agent burns its context reading files. This stops it — and shows you the receipt.**

[](https://github.com/Habartru/token_save_mcp/actions/workflows/ci.yml) [](https://pypi.org/project/token-save-mcp/) [](https://github.com/Habartru/token_save_mcp/blob/main/LICENSE) [](https://www.python.org/downloads/)

An MCP server that sends big files to a cheap worker model and returns only the answer. The file bytes are paid for once, in the worker's context — not permanently in your agent's.


The hook **blocks** the expensive read and redirects it. The answer comes back with the worker's **real token usage from the API response** — not an estimate, a receipt:

─────────────────────────────────────────────────────────────
token-save: 1 file, 606 lines | direct read ≈7,042 tok →
into context ≈234 tok (saved 6,808 · 97%)
worker: glm-5.3-flash | 6,155 in / 278 out | 4.0s

---

Install

pip install token-save-mcp
token-save-mcp init

`init` finds a provider key you already have and sets everything up. If you have none, it prints the options and where to get one — nothing is connected automatically, and no key ships with the tool. **The worker is yours**: your key, your provider, your bill.

A full run looks like this:

export OPENROUTER_API_KEY=sk-or-...        # your key, from your provider
token-save-mcp init --provider openrouter --hook

Verify with `token-save-mcp doctor`, which checks the config and makes one live call to prove the worker answers:

✓ provider: openrouter -> https://openrouter.ai/api/v1
✓ worker model: deepseek/dee