MCPMarket
스킬 판매Power Your Agents연결
  1. 홈
  2. 서버
  3. Scampi

Scampi

ajhcsbyajhcs
•
1
•
생산성 및 워크플로
개발자 도구
데이터 과학 및 ML

Orchestrates external LLM tokens to offload high-volume tasks from Claude Code, enhancing its capabilities and efficiency.

Run on MCP Market

One-click cloud hosting

Related MCPs

View more
  • smithery-ai

    Obsidian Connector

    Connects Claude Desktop to read and search your Obsidian vault's Markdown notes.

  • resend

    Send Email

    Enables sending emails directly from Cursor or Claude Desktop using the Resend API.

  • 21st-dev

    Magic

    Generate modern UI components instantly from natural language descriptions within your IDE.

Related Skills

View all
  • openclaw

    Diagram Maker & Visualizer

    Generates professional SVG, HTML, and Excalidraw diagrams for software architecture, system flows, and educational concepts.

  • openclaw

    GH Issues Auto-Fixer

    Automates the end-to-end GitHub issue lifecycle by spawning sub-agents to implement code fixes, open pull requests, and resolve review comments.

  • openclaw

    Discord Integration

    Manages Discord operations including messaging, reactions, and channel management directly through Claude.

MCPMarket

Claude 및 Cursor와 같은 MCP 클라이언트를 즐겨 사용하는 도구에 연결하는 MCP 서버를 찾아보세요. MCP 마켓에서 시작하세요.

둘러보기

  • MCP 검색
  • MCP 서버
  • MCP 클라이언트
  • Claude 스킬
  • MCP Market Hub
  • 카테고리
  • MCP 서버란 무엇인가요?
  • Model Context Protocol

순위

  • 오늘의 인기 MCP
  • 오늘의 인기 Claude 스킬
  • Claude 스킬 Top 100
  • MCP 서버 Top 100

소개

  • 뉴스
  • 제출하기
  • 문의하기

© 2026 MCP 마켓. 모든 권리 보유.·Privacy·Terms

Scampi is an MCP server designed to integrate with Claude Code, enabling it to leverage external Large Language Models (LLMs) for high-volume, token-intensive tasks. This allows Claude Code to offload bulk processing to cheaper local LLM servers (like LM Studio, Ollama, llama.cpp, text-generation-webui) or cloud providers (Z.ai), reserving Claude's context for higher-level judgment and reasoning. Scampi provides a suite of tools for tasks such as indexing codebases for semantic search, generating multiple solution approaches in parallel, and brainstorming diverse ideas, all while managing concurrency and caching for optimal performance.

주요 기능

01Multi-provider LLM support for local and cloud models
02Auto-detection of running local LLM servers
03Codebase mapping with semantic summaries and incremental caching
04Parallel generation of multiple coding solutions or brainstormed approaches
05Token arbitrage to optimize LLM cost and performance
061 GitHub stars

사용 사례

01Generating diverse coding solutions in parallel for complex development tasks
02Indexing and searching large codebases with natural language queries
03Quickly brainstorming multiple architectural approaches or implementation ideas
04Retrieving specific file contents and dependency graph information from a project