MCP Directory

rushikeshmore/CodeCortex

GitHub
Productivity

Persistent codebase knowledge layer for AI coding agents. Pre-digests codebases into structured knowledge (symbols, dependency graphs, co-change patterns, architectural decisions) via tree-sitter native parsing (28 languages) and serves via MCP. 14 tools, ~85% token reduction. Works with Claude Code, Cursor, Codex, and any MCP client.

Direct install

Run the underlying MCP server directly — without Agent-CoreX routing.

npx -y codecortex

Use with Agent-CoreX

Agent-CoreX intelligently routes which tools from rushikeshmore/CodeCortex your AI agent actually needs per request — reducing token usage and cost.

agent-corex.json

{
  "mcpServers": {
    "codecortex": {
      "command": "npx",
      "args": [
        "-y",
        "codecortex"
      ]
    }
  }
}

Route rushikeshmore/CodeCortex intelligently

Connect in 2 minutes. Only pay for the tools your agent actually uses.

Installation Guide

Use with Agent-CoreX

Recommended: intelligent tool routing, lower costs

uvx agent-corex mcp add codecortex

Agent-CoreX selects only the tools your agent needs, cutting token usage by up to 60%.

Direct Install

Use rushikeshmore/CodeCortex directly without routing

npx -y codecortex

New to Agent-CoreX? View setup guide →

rushikeshmore/CodeCortex MCP Server — Agent-CoreX