MCP Codebase Index Server

AI-powered semantic search for your codebase in GitHub Copilot, Kiro, and other MCP-compatible editors

typescript

GitHub Stars

typescript

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "ngotaico-mcp-codebase-index": {
      "command": "npx",
      "args": [
        "-y",
        "@ngotaico/mcp-codebase-index"
      ],
      "env": {
        "REPO_PATH": "/absolute/path/to/your/project",
        "QDRANT_URL": "https://your-cluster.gcp.cloud.qdrant.io:6333",
        "GEMINI_API_KEY": "AIzaSyC...",
        "QDRANT_API_KEY": "eyJhbGci..."
      }
    }
  }
}

MCP Codebase Index Server provides AI-powered semantic search over your codebase, enabling editors and CLI tools to find meaning and structure across large codebases. It leverages Gemini embeddings and Qdrant vector storage to index, search, and visualize code relationships, helping you understand architecture, locate related functionality, and accelerate development.

How to use

You connect your editor or CLI to the MCP Codebase Index Server to search your codebase by meaning rather than just keywords. Start the server in your development environment, ensure your codebase is indexed, and then issue natural-language queries like “Find the authentication logic” or “Visualize my codebase” to discover relevant code paths and modules. You can also check indexing status and export visualizations for deeper analysis.

How to install

Prerequisites you need before installation:

Node.js and npm installed on your machine.
Gemini API key from Google AI Studio.
Qdrant Cloud account with an endpoint and API key.

Install and run the MCP server

Available tools

Semantic Search

Query code by meaning using AI embeddings to retrieve semantically relevant results.

Smart Chunking

Automatically split code into logical units like functions and classes for better search granularity.

Incremental Indexing

Only re-index files that changed to save time on updates.

Auto-save Checkpoints

Save progress periodically so you can resume indexing after interruptions.

Real-time Progress

View ETA and performance metrics during indexing.

Parallel Processing

Index in parallel with batch execution for faster throughput.

Real-time Watch

Automatically update the index when files change.

Vector Storage

Store embeddings persistently in a Qdrant vector store.

Prompt Enhancement

Optional AI-powered improvements to search queries for better results.

Vector Visualization

Visualize code relationships in 2D/3D to understand structure.

Built by

VeilStrat

AI signals for GTM teams