ooples/token-optimizer-mcp 是从 https://github.com/ooples/token-optimizer-mcp. 导入的 MCP 服务器候选
概览
ooples/token-optimizer-mcp 是从 https://github.com/ooples/token-optimizer-mcp. 导入的 MCP 服务器候选
概述（AI 翻译）
令牌优化器MCP
压缩来优化你的账单，而不是字节数—— 并且会发送基调，方便你查看。
一个本地账本，用于优化工具、实时图替换、每个代理以及图自身成本。
与HeadRoom相比如何
提供者缓存提示前缀：缓存的令牌在0.1x处重读，重写 有些压缩器计费是1.25倍。大多数压缩器会优化去除的字节，忽略这个数字 乘数。这个能优化账单。
以他们实际的实际表现、在他们自己的装置上进行衡量。 不是 重新实现，而不是我们的固定装置：它们的束缚会压缩有效载荷， 抛售后，他们的解析器兑换了自己的标记，而我们的标记器则被交给了 字节相同。他们的列是九种配置中最好的， 一行一行地捕获。
我们的两只手臂在桌子上，回答不同的问题。ours
是无处移动方块的模块引擎，MCP工具和
挂钩运行：它移除的所有东西，都是通过压缩去除的，什么都不做
离开请求。ours, proxy 是 Claude Code 会话运行的代理
本页由 AI 翻译，技术细节请以原文为准。
README
以下为原文 README 节选，完整内容请查看原文。
Token Optimizer MCP
Compression that optimises your bill, not your byte count — and ships the benchmark so you can check it.
One local ledger for optimizer tools, live-graph substitutions, every agent, and the graph’s own cost.
How it compares to Alternative A
Providers cache the prompt prefix: cached tokens re-read at 0.1x, rewritten ones bill at 1.25x. Most compressors optimise bytes removed and ignore that multiplier. This one optimises the bill.
Measured against their real implementation, on their own fixtures. Not a reimplementation and not our fixtures: their harness compresses the payload, dumps it, their resolver redeems their own markers, and ours is handed the identical bytes. Their column is the best of the nine configurations that capture holds, row by row.
Two of our arms are in the table, and they answer different questions. ours
is the block engine with nowhere to move a block, which is how the MCP tools and
the hooks run: everything it removes, it removes by compressing, and nothing
leaves the request. ours, proxy is the proxy a Claude Code session runs
安装
npx -y @ooples/token-optimizer-mcp@latest配置
{
"mcpServers": {
"token-optimizer": {
"type": "local",
"command": "npx",
"args": ["-y", "@ooples/token-optimizer-mcp@latest"],
"tools": ["*"]
}
}
}