Skip to main content
Glama
deenesjakoruzh
Yang1Bai

claw-tsaver

by Yang1Bai
OverviewSchemaRelated ServersScoreDiscussions
Python
Local

claw-tsaver

专为 OpenClaw 用户设计的节省 Token 的 MCP 代理。通过延迟展开技术，将工具调用负载减少 90% 以上。

为什么使用它

MCP 工具调用通常会在单次响应中返回数千个 Token 的 HTML 或 JSON 数据，但模型通常只使用其中的 5%。剩下的 95% 会在无形中消耗上下文窗口并增加成本。claw-tsaver 位于 OpenClaw 和您的下游 MCP 服务器之间，拦截过大的响应，并向模型提供紧凑的预览和按需获取的句柄。

Related MCP server: TokenSaver MCP

如何工作

sequenceDiagram
    participant U as OpenClaw (Claude)
    participant C as claw-tsaver proxy
    participant F as fetch / puppeteer / etc.
    U->>C: call_tool("fetch", url)
    C->>F: forward call
    F-->>C: 11,507 tokens of HTML
    Note over C: tiktoken count > threshold
    C->>C: store full content in SQLite
    C-->>U: {preview_head, preview_tail, expand_handle}<br/>(only 104 tokens)
    Note over U: model decides if it needs full text
    U->>C: expand_content(handle)
    C-->>U: full 11,507 tokens

实际测量

测试

原始 Token 数

返回 Token 数

节省比例

获取维基百科 "Tokenization (data security)"

11,507

104

99.1%

测试环境：OpenClaw + Claude Sonnet 4.6 + mcp-server-fetch，2026-04-25。 原始数据：benchmarks/mvp-day1-fetch.jsonl。

快速开始

1. 前置要求

安装 uv（仅需设置一次）：

curl -LsSf https://astral.sh/uv/install.sh | sh

无需安装 claw-tsaver —— uvx 会按需获取并运行它。

2. 配置下游 MCP 服务器

编辑 ~/.claw-tsaver/config.json（首次运行 claw-tsaver-mcp 时会自动创建模板）：

{
  "downstream_servers": [
    {"name": "fetch", "command": "uvx", "args": ["mcp-server-fetch"]}
  ],
  "compression_threshold_tokens": 500
}

3. 在 OpenClaw 中注册

在 ~/.openclaw/openclaw.json 的顶层添加此代码块：

"mcp": {
  "servers": {
    "claw-tsaver": {
      "command": "uvx",
      "args": ["--from", "git+https://github.com/Yang1Bai/claw-tsaver",
               "claw-tsaver-mcp"]
    }
  }
}

然后重启 OpenClaw 网关：openclaw gateway restart

仪表盘

可选：用于实时查看 Token 节省统计数据的本地 Web UI。

uvx --from git+https://github.com/Yang1Bai/claw-tsaver claw-tsaver-dashboard

在浏览器中打开 http://localhost:7878。

路线图

  • [x] 模块 A：延迟展开代理（本次发布）

  • [x] 模块 D：本地仪表盘（本次发布）

  • [ ] 模块 B：工具路由（每轮仅自动加载相关的 MCP）

  • [ ] 模块 C：对话历史压缩（原子事实卡片）

许可证

MIT — 详见 LICENSE 文件。

贡献

欢迎提交 Issue 和 PR。

Install Server
A
license - permissive license
A
quality
C
maintenance

How are these scores calculated?

Maintenance

–Maintainers
–Response time
–Release cycle
1Releases (12mo)
Commit activity

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Tools

Related MCP Servers

  • toon-parse-mcp

    ankitpal181
    A
    license
    Not graded
    quality
    D
    maintenance
    An MCP server that helps AI agents reduce token usage by converting data to TOON format and stripping comments and unnecessary whitespace from code files.
    MIT

  • TokenSaver MCP

    pozii
    A
    license
    A
    quality
    C
    maintenance
    An MCP server that reduces AI API costs by up to 97% through token measurement, compression, caching, and pruning, all without changing prompts.
    10
    1
    Apache 2.0

  • token-filter-mcp

    VMexicano
    A
    license
    A
    quality
    A
    maintenance
    An MCP server that intelligently filters and compresses tool outputs to reduce context window usage, saving up to 90% of tokens by removing noise such as passing tests and redundant information.
    5
    20
    MIT

  • smart-context-mcp

    Arrayo
    A
    license
    Not graded
    quality
    C
    maintenance
    MCP server that reduces AI agent token usage by up to 90% through intelligent context compression. Enables efficient code exploration, multi-file refactoring, and debugging by providing tools for smart reading, searching, and managing code context.
    4
    MIT

View all related MCP servers

Related MCP Connectors

View all MCP Connectors

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/Yang1Bai/claw-tsaver'

If you have feedback or need assistance with the MCP directory API, please join our Discord server