MCP Directory
Back

trace-mcp

by nikolai-vysotskyi · TypeScript · ★ 89

MCP server for Claude Code and Codex. One tool call replaces ~42 minutes of agent exploration

#ai-agents#claude#claude-ai#claude-code#claude-code-plugin#claude-code-skill#claude-desktop#claude-skill#claude-skills#code-intelligence#codex#codex-skill#developer-tools#knowledge-graph#mcp#mcp-server#rag#token#token-savings#tokens

Install

npx -y github:nikolai-vysotskyi/trace-mcp

Auto-generated from the repo's primary language — check the repo's own README for its exact install instructions.

Claude Desktop config

A starting point for your claude_desktop_config.json (auto-generated — the repo's README may specify a published package name or required env vars):

{
  "mcpServers": {
    "trace-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "github:nikolai-vysotskyi/trace-mcp"
      ]
    }
  }
}

From the README

trace-mcp AI agents recompute the same work. trace-mcp makes them reuse instead. The recomputation → reuse layer for AI systems. 40–50% fewer tokens on average  ·  up to 2× effective capacity  ·  up to 99% less redundant processing Based on early benchmarks across agent workflows with repeated context and dependency traversal. > AI systems don't scale because they recompute instead of reuse. Every turn, the agent re-reads the same files, re-traverses the same dependencies, and re-inflates the context window with structure it alr…
Read full README on GitHub →

Related ai & ml servers