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.
MCP
CSCSoftware/AiDex
Added 1 June 2026
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-Projectaidex_initaidex_queryaidex_signatureaidex_signaturesaidex_updateaidex_removeaidex_summaryaidex_treeaidex_describeaidex_linkaidex_unlinkaidex_linksaidex_statusaidex_scanaidex_filesaidex_noteaidex_sessionaidex_vieweraidex_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
Pairs with
Other entries in the index that connect to this one. Click through to see the chain.
Claude Code
Anthropic
Anthropic's terminal-native coding agent. Reads your repo, edits files, runs tests, ships PRs.
Continue
Continue.dev
Open-source AI code assistant for VS Code and JetBrains. Customisable, BYO model, built for enterprise.
Cline
Cline
Open-source autonomous coding agent that lives inside VS Code. BYO model key, watch it work.
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.