Skip to content

Quickstart

  • An IntelliRag account with an API key
  • Git installed
  • A code repository to index
  1. Create a workspace and repository

    Log in to the dashboard and create a workspace. Add a repository by providing the git remote URL.

  2. Install the indexer

    Terminal window
    go install github.com/intellirag/intellirag.io/indexer/cmd/indexer@latest
  3. Run the indexer

    Terminal window
    indexer index \
    --api-url https://api.intellirag.io \
    --api-key your-api-key

    That’s it. --repo-path defaults to the current directory (.), so just run from your repo root. The indexer auto-resolves the repository from git remote get-url origin. It will exit with an error if the current directory is not a git repository.

  4. Install the MCP server

    Add to your Claude Code MCP config:

    {
    "mcpServers": {
    "intellirag": {
    "command": "irag-mcp",
    "env": {
    "RAG_API_URL": "https://mcp.intellirag.io",
    "RAG_API_KEY": "your-api-key"
    }
    }
    }
    }
  5. Ask your AI assistant about your code

    The MCP tools are available automatically. Try asking:

    • “What does the UserService class do?”
    • “Show me all HTTP endpoints in this repo”
    • “What would be affected if I change the findById method?”

The indexer extracts:

Data Description
Symbols Functions, classes, methods, interfaces, constants
Call edges Who calls what, including method dispatch
Import edges Module and package dependencies
Entry points HTTP routes, event handlers, CLI commands
Data flow Parameter propagation and return values
Tech debt TODO/FIXME/HACK markers with context
Patterns Framework usage, design patterns, anti-patterns
Config keys Application configuration with sources and consumers
Schemas Database table definitions from DDL and migrations
Contracts API contracts from OpenAPI/Swagger specifications