jscpd

Active
GitHub TypeScript MIT

Description

jscpd is a code duplication detector that finds copy-pasted code across large repositories, useful as a code-quality signal for coding agents.

Key Features

  • Copy-paste detector supporting 223 languages and formats
  • Multiple output formats including console, JSON, HTML, and XML reports
  • MCP protocol integration so AI agents can query similarity in real time
  • High accuracy with hybrid token and AST based algorithms
  • Flexible thresholds configurable for minimum lines and tokens of duplicated code

Use Cases

💡 Detect newly added duplicate code in CI and block low-quality merges
💡 Let AI coding agents self-check for duplication before commits
💡 Audit code reuse across a large codebase
💡 Use MCP to surface duplicates in real time inside the IDE or editor

Strengths & Limitations

Strengths

  • Actively maintained, recent updates
  • High community interest (6.0k stars)
  • Permissive open-source license (MIT)
  • Responsive to issues, low backlog

Quick Start

# Install jscpd globally
npm install -g jscpd

# Run detection in the project
jscpd ./src

# Start MCP server for agent queries
jscpd --mcp ./src

# Output an HTML report
jscpd --reporters html ./src

Related Projects

DevDocs MCP

2.1k · TypeScript
Stale B

Free, private, UI-based tech documentation MCP server designed for coders and AI coding assistants with precise doc retrieval.

mcpdocumentationdeveloper-tools +1
  • · Intelligent web crawling with smart depth control (1-5 levels) and automatic link discovery
  • · Parallel processing with smart caching for high-speed documentation extraction at 1000 pages/min
  • · MCP server integration for direct AI-powered querying of crawled documentation

Context Mode

19.9k · TypeScript
Active A

Context Mode is a context window optimization tool for AI coding agents that sandboxes tool output for 98% context reduction across 12 major platforms.

context-optimizationmcpclaude-code +2
  • · Sandboxes tool output, reducing 315KB raw data to 5.4KB — a 98% context reduction
  • · SQLite + FTS5 session continuity that recovers key context via BM25 search after conversation compaction
  • · Think in Code paradigm: LLM writes analysis scripts instead of processing raw data, saving 100x context