Codebase Index
Enables semantic search across your codebase using Google's Gemini embeddings and Qdrant Cloud vector storage. Supports 15+ programming languages with smart code chunking and real-time file change monitoring.
What is Codebase Index?
Codebase Index is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to enables semantic search across your codebase using google's gemini embeddings and qdrant cloud vector storage. supports 15+ programming languages with smart code chunking and real-time file change mon...
Enables semantic search across your codebase using Google's Gemini embeddings and Qdrant Cloud vector storage. Supports 15+ programming languages with smart code chunking and real-time file change monitoring.
This server falls under the Developer Tools category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- Enables semantic search across your codebase using Google's
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx mcp-codebase-indexConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Codebase Index
MCP Codebase Index is a semantic search server that indexes your entire codebase using Google Gemini embeddings stored in a Qdrant Cloud vector database. It supports 15+ programming languages through AST-aware chunking, monitors files for changes in real time, and provides ~90% faster incremental re-indexing compared to full scans. Developers use it to ask natural-language questions like 'find the authentication logic' and receive semantically relevant code segments, or to generate interactive 2D/3D visualizations of codebase structure.
Prerequisites
- Python 3.9+ or Node.js for running the server via npx
- A Google AI Studio account and Gemini API key (GEMINI_API_KEY)
- A Qdrant Cloud account with a cluster URL and API key
- An MCP-compatible client such as Claude Desktop or VS Code with Copilot
Obtain required API keys
Create a Gemini API key at Google AI Studio (aistudio.google.com) and create a free Qdrant Cloud cluster at cloud.qdrant.io. Note the cluster URL and API key from the Qdrant dashboard.
Install the MCP server
Install the package globally or run it directly via npx. The official package is published under the @ngotaico scope.
npx -y @ngotaico/mcp-codebase-indexConfigure environment variables
Set the four required environment variables: your repository path, Gemini API key, Qdrant cluster URL, and Qdrant API key. Optional variables let you customize the collection name, batch size, and embedding model.
Add the server to your MCP client
Edit claude_desktop_config.json to add the server entry with all required environment variables.
Trigger initial indexing
After connecting, ask the assistant to index your project. The server will chunk code using AST parsing, generate embeddings via Gemini, and store them in Qdrant. Subsequent runs use incremental updates.
Codebase Index Examples
Client configuration
Add this to your claude_desktop_config.json. Replace the placeholder values with your actual paths and API keys.
{
"mcpServers": {
"codebase-index": {
"command": "npx",
"args": ["-y", "@ngotaico/mcp-codebase-index"],
"env": {
"REPO_PATH": "/absolute/path/to/your/project",
"GEMINI_API_KEY": "AIzaSyC...",
"QDRANT_URL": "https://your-cluster.gcp.cloud.qdrant.io:6333",
"QDRANT_API_KEY": "your-qdrant-api-key",
"WATCH_MODE": "true",
"BATCH_SIZE": "50"
}
}
}
}Prompts to try
Semantic search and visualization prompts you can use after indexing your codebase.
- "Find the authentication and JWT validation logic in the codebase"
- "Where is database connection pooling configured?"
- "Show me all error handling patterns used across the project"
- "Visualize my codebase to see how modules are clustered"
- "Check the indexing status and tell me how many files have been processed"Troubleshooting Codebase Index
Indexing stalls or produces no results
Verify REPO_PATH is an absolute path and that the directory exists. Check that GEMINI_API_KEY is valid by testing it in Google AI Studio. Qdrant connection errors will appear in the server logs—confirm the QDRANT_URL includes the port (6333).
Search returns irrelevant results
Enable PROMPT_ENHANCEMENT=true to let the server improve your queries before embedding. Also ensure the initial index is complete by checking indexing status before running searches.
File changes are not picked up automatically
Set WATCH_MODE=true in your environment variables to enable real-time file monitoring. Without this, the index reflects only the state at the last manual indexing run.
Frequently Asked Questions about Codebase Index
What is Codebase Index?
Codebase Index is a Model Context Protocol (MCP) server that enables semantic search across your codebase using google's gemini embeddings and qdrant cloud vector storage. supports 15+ programming languages with smart code chunking and real-time file change monitoring. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Codebase Index?
Follow the installation instructions on the Codebase Index GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Codebase Index?
Codebase Index works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Codebase Index free to use?
Yes, Codebase Index is open source and available under the MIT License license. You can use it freely in both personal and commercial projects.
Codebase Index Alternatives — Similar Developer Tools Servers
Looking for alternatives to Codebase Index? Here are other popular developer tools servers you can use with Claude, Cursor, and VS Code.
Ecc
★ 188.2kThe agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
Javaguide
★ 155.8kJava 面试 & 后端通用面试指南，覆盖计算机基础、数据库、分布式、高并发、系统设计与 AI 应用开发
Gemini CLI
★ 104.5kA secure MCP server that wraps the Google Gemini CLI, allowing clients to query Gemini models using local OAuth sessions without requiring an API key. It provides tools for model interaction and diagnostics with built-in protection against command in
Awesome MCP Servers
★ 87.3k⭐ Curated list of Model Context Protocol (MCP) servers - tools that extend Claude Desktop, Cursor, Windsurf, and other MCP clients with custom capabilities.
MCP Servers
★ 86.0kModel Context Protocol Servers
CC Switch
★ 77.5kA cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Gemini CLI & Hermes Agent. Only official website: ccswitch.io
Browse More Developer Tools MCP Servers
Explore all developer tools servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Codebase Index in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Codebase Index?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.