Skip to main content
Glama

MCP Codebase Index

by NgoTaiCo
QUICK_REF.md•3.4 kB
# MCP Codebase Index - Quick Reference One-page cheat sheet for fast setup and troubleshooting. --- ## Required Config **All 4 variables are mandatory:** ```json { "mcpServers": { "codebase": { "command": "npx", "args": ["-y", "@ngotaico/mcp-codebase-index"], "env": { "REPO_PATH": "/Users/you/Projects/myapp", "GEMINI_API_KEY": "AIzaSyC...", "QDRANT_URL": "https://xxx.gcp.cloud.qdrant.io:6333", "QDRANT_API_KEY": "eyJhbGci..." } } } } ``` --- ## Optional Config ```json { "env": { "QDRANT_COLLECTION": "my_project", "WATCH_MODE": "true", "BATCH_SIZE": "50" } } ``` --- ## Get Credentials ### Gemini API Key 1. Go to [aistudio.google.com/app/apikey](https://aistudio.google.com/app/apikey) 2. Click "Create API Key" 3. Copy key (starts with `AIzaSy...`) ### Qdrant Cloud 1. Sign up at [cloud.qdrant.io](https://cloud.qdrant.io) 2. Create cluster (free tier) 3. Copy cluster URL: `https://xxx.gcp.cloud.qdrant.io:6333` 4. Create API key: JWT token starting with `eyJhbGci...` šŸ“– **Detailed guide**: [QDRANT_CLOUD_SETUP.md](QDRANT_CLOUD_SETUP.md) --- ## Config File Location **macOS:** ```bash ~/Library/Application Support/Claude/claude_desktop_config.json ``` **Windows:** ``` %APPDATA%\Claude\claude_desktop_config.json ``` **Linux:** ```bash ~/.config/Claude/claude_desktop_config.json ``` --- ## Usage Examples ``` "Find the authentication logic" "Show me database connection code" "Where is error handling implemented?" "Find all API endpoints" ``` --- ## Troubleshooting ### Check Logs ```bash # macOS/Linux tail -f ~/Library/Logs/Claude/mcp*.log # Windows Get-Content "$env:APPDATA\Claude\logs\mcp*.log" -Wait ``` ### Test Qdrant Connection ```bash curl -H "api-key: YOUR_KEY" \ https://YOUR_CLUSTER.gcp.cloud.qdrant.io:6333/collections ``` ### Common Issues āœ… **Server not appearing?** - Restart Claude Desktop - Check all 4 env variables are set - Verify `REPO_PATH` is absolute path āœ… **Can't connect to Qdrant?** - Check URL includes `:6333` port - Verify API key is correct - Check cluster is running āœ… **Indexing too slow?** - Large repos take 5-10 minutes - Reduce `BATCH_SIZE` to 20-30 - Check Gemini API quota āœ… **Search returns nothing?** - Wait for indexing to complete - Try more specific queries - Check logs for errors --- ## Environment Variables | Variable | Required | Default | Description | |----------|----------|---------|-------------| | `REPO_PATH` | āœ… | - | Absolute path to project | | `GEMINI_API_KEY` | āœ… | - | Google Gemini API key | | `QDRANT_URL` | āœ… | - | Qdrant cluster URL | | `QDRANT_API_KEY` | āœ… | - | Qdrant Cloud API key | | `QDRANT_COLLECTION` | āŒ | `codebase` | Collection name | | `WATCH_MODE` | āŒ | `true` | Auto-update files | | `BATCH_SIZE` | āŒ | `50` | Embedding batch size | --- ## Supported Languages Python • TypeScript • JavaScript • Dart • Go • Rust • Java • Kotlin • Swift • Ruby • PHP • C • C++ • C# • Shell --- ## Links - **NPM**: [npmjs.com/package/@ngotaico/mcp-codebase-index](https://www.npmjs.com/package/@ngotaico/mcp-codebase-index) - **GitHub**: [github.com/NgoTaiCo/mcp-codebase-index](https://github.com/NgoTaiCo/mcp-codebase-index) - **Issues**: [github.com/NgoTaiCo/mcp-codebase-index/issues](https://github.com/NgoTaiCo/mcp-codebase-index/issues)

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/NgoTaiCo/mcp-codebase-index'

If you have feedback or need assistance with the MCP directory API, please join our Discord server