Enterprise DNA
M MCP Servers Developer low

CSCSoftware/AiDex

by Various

MCP Server for persistent code indexing. Gives AI assistants (Claude, Gemini, Copilot, Cursor) instant access to your codebase. 50x less context than grep.

C

MCP

CSCSoftware/AiDex

Added 1 June 2026

#ai-coding #claude #claude-code #code-indexing #code-search #copilot #cursor #developer-tools

Overview

AiDex is an MCP server that indexes a codebase persistently, allowing AI assistants like Claude, Gemini, Copilot, and Cursor to query it with minimal context. It claims to use 50x less context than grep by pre-indexing code structure and content.

Best for

Best for
Developers using AI coding assistants who work with large codebases and want to minimize context token usage.

Use cases

  • Give an AI assistant instant access to a large codebase without loading the entire repo
  • Reduce context usage when asking AI tools about code structure or function locations
  • Enable persistent code search across sessions without re-scanning files

How to use

Install

npm install -g aidex-mcp

Tools exposed

  • Cross-Project
  • aidex_init
  • aidex_query
  • aidex_signature
  • aidex_signatures
  • aidex_update
  • aidex_remove
  • aidex_summary
  • aidex_tree
  • aidex_describe
  • aidex_link
  • aidex_unlink
  • aidex_links
  • aidex_status
  • aidex_scan
  • aidex_files
  • aidex_note
  • aidex_session
  • aidex_viewer
  • aidex_task

Tested with

Claude Desktop, Claude Code, Cursor, Windsurf, VS Code, ChatGPT

Notes

AiDex is an MCP server that indexes a codebase persistently, allowing AI assistants like Claude, Gemini, Copilot, and Cursor to query it with minimal context. It claims to use 50x less context than grep by pre-indexing code structure and content.

34 stars on GitHub. Last updated 2026-05-31. Licensed MIT.

Use cases

  • Give an AI assistant instant access to a large codebase without loading the entire repo
  • Reduce context usage when asking AI tools about code structure or function locations
  • Enable persistent code search across sessions without re-scanning files

Pros

  • Dramatically reduces context overhead compared to grep-based approaches
  • Works with multiple popular AI assistants and IDEs
  • Persistent indexing avoids repeated file scanning

Cons

  • Low GitHub star count (34) suggests limited community adoption or maturity
  • Requires setup and maintenance of an MCP server
  • Indexing may become stale if codebase changes frequently without re-indexing

Indexed from awesome-mcp-servers-punkpeye and enriched against its public facts.

Pros

  • Dramatically reduces context overhead compared to grep-based approaches
  • Works with multiple popular AI assistants and IDEs
  • Persistent indexing avoids repeated file scanning

Cons

  • Low GitHub star count (34) suggests limited community adoption or maturity
  • Requires setup and maintenance of an MCP server
  • Indexing may become stale if codebase changes frequently without re-indexing
Free 27-page guide

Get the free Developer’s Field Guide

A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.

Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.

No spam. Unsubscribe any time.

Running a business, not writing the code? See the MCP servers picked for operators, and get your first one wired up with us.

Operator picks