trace-mcp
Active·★ 193·MIT·Updated 2026-10-22
trace-mcp is a framework-aware code intelligence MCP server that builds cross-language dependency graphs from source code. It enables AI agents to understand framework-specific relationships, track request flows, analyze change impact, and remember past decisions across sessions, significantly reducing token usage.
#ai-agents#claude-code#code-intelligence#developer-tools#mcp#mcp-server#mcp-servers#static-analysis
01
Features
01Framework-aware dependency graph across languages
02Code-linked decision memory
03Cross-session intelligence and context carryover
04Change impact analysis with risk scoring
05Up to 99% token reduction
02
Compatibility
Claude Code
Claude Code
Verified via docs
Cursor
Cursor
Verified via docs
Windsurf
Windsurf
Verified via docs
Claude Desktop
Claude Desktop
Verified via docs
03
Quick start
1
$ npm install -g trace-mcp
2
$ trace-mcp init
3
$ trace-mcp add
04
Use cases
↳Understanding full-stack web applications with cross-language relationships
↳Impact analysis for changes across multiple languages and frameworks
↳Reducing token consumption and context window pressure in large codebases
05
Alternatives
qartez-mcp★ 73
Semantic code intelligence MCP server for Claude Code - project maps, symbol search, impact analysis, and more
codescout★ 27
High-performance coding agent toolkit MCP server — IDE-grade code intelligence for LLMs
Charles-mcp★ 327
Charles Proxy MCP server for AI agents with live capture, structured traffic analysis, and agent-friendly tool contracts
turbomcpstudio★ 38
A native desktop application for developing, testing, and debugging Model Context Protocol servers.
codelogic-mcp-server★ 37
An MCP Server to utilize Codelogic's rich software dependency data in your AI programming assistant.
Comments
Log in to leave a comment
No comments yet. Be the first!