Skip to main content
Glama
deenesjakoruzh
Yang1Bai

claw-tsaver

by Yang1Bai
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

claw-tsaver

OpenClaw 사용자를 위한 토큰 절약 MCP 프록시입니다. 지연 확장을 통해 도구 호출 페이로드를 90% 이상 줄여줍니다.

이유

MCP 도구 호출은 종종 단일 응답에서 수천 개의 HTML 또는 JSON 토큰을 반환하지만, 모델은 일반적으로 그중 5%만 사용합니다. 나머지 95%는 컨텍스트 창을 낭비하고 비용을 증가시킵니다. claw-tsaver는 OpenClaw와 하위 MCP 서버 사이에 위치하여, 너무 큰 응답을 가로채고 모델에게 압축된 미리보기와 온디맨드 핸들을 제공합니다.

Related MCP server: TokenSaver MCP

작동 방식

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

실제 측정 결과

테스트

원본 토큰

반환된 토큰

절감액

위키백과 "토큰화(데이터 보안)" 가져오기

11,507

104

99.1%

OpenClaw + Claude Sonnet 4.6 + mcp-server-fetch에서 테스트됨, 2026-04-25. 원시 데이터: benchmarks/mvp-day1-fetch.jsonl.

빠른 시작

1. 사전 요구 사항

uv를 설치하세요 (1회 설정):

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

claw-tsaver를 별도로 설치할 필요는 없습니다. uvx가 필요할 때 가져와서 실행합니다.

2. 하위 MCP 서버 구성

~/.claw-tsaver/config.json을 편집하세요 (claw-tsaver-mcp를 처음 실행하면 템플릿이 자동으로 생성됩니다):

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

3. OpenClaw에 등록

~/.openclaw/openclaw.json의 최상위 수준에 이 블록을 추가하세요:

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

그런 다음 OpenClaw 게이트웨이를 다시 시작하세요: openclaw gateway restart

대시보드

선택 사항: 실시간 토큰 절감 통계를 위한 로컬 웹 UI입니다.

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

브라우저에서 http://localhost:7878을 여세요.

로드맵

  • [x] 모듈 A: 지연 확장 프록시 (이번 릴리스)

  • [x] 모듈 D: 로컬 대시보드 (이번 릴리스)

  • [ ] 모듈 B: 도구 라우팅 (턴당 관련 MCP만 자동 로드)

  • [ ] 모듈 C: 대화 기록 압축 (원자적 사실 카드)

라이선스

MIT — LICENSE 파일을 참조하세요.

기여

이슈 및 PR을 환영합니다.

Available Tools

1 tool
expand_contentA

Retrieve the full content of a previously compressed tool result. Pass the expand_handle returned in the compressed envelope.

ParametersJSON Schema
NameRequiredDescriptionDefault
handleYesThe expand_handle from a compressed result.

TDQS

A4.2/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided; description implies a read operation but does not detail any side effects, auth requirements, or handle expiration.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two efficient sentences front-load the purpose with no wasted words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a single-parameter tool with no output schema, the description sufficiently guides usage, though output format is unstated.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The description adds context that the handle comes from a compressed envelope, complementing the schema's parameter description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool retrieves the full content of a compressed result, using specific verb and resource.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description instructs to pass the expand_handle from a compressed envelope, implying the usage context, but lacks explicit conditions or exclusions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

  1. 1 tool updatev0.0.1
    • First observedexpand_content
Deploy Server
Shareable, User-Owned Context BackendPeople, applications, and agents read, write, and coordinate together in one context lake. Reach it over MCP, a CLI, a Python SDK, or REST.fulcradynamics.comAd

TDQS

A4.1/5.0

Scored across 1 tool

Disambiguation5/5

Only one tool exists, so there is no potential for confusion between different tools.

Naming Consistency5/5

With a single tool, there is no naming inconsistency to evaluate; the name 'expand_content' is clear and descriptive.

Tool Count2/5

A single tool for expanding compressed results is very thin; the server likely needs additional tools (e.g., for listing handles) to be useful as an MCP server.

Completeness4/5

The tool covers its stated purpose of retrieving full content, but the server lacks any supporting tools for compression or handle management, leaving a minor gap in the overall surface.

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources

Related MCP Connectors

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.
    31 PyPI
    MIT

  • TokenSaver MCP

    pozii
    A
    license
    A
    quality
    D
    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
    B
    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
    12 npm
    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