docker-compose up -d

docker-compose down

{
  "mcpServers": {
    "rag-docs": {
      "command": "node",
      "args": ["/path/to/your/mcp-ragdocs/build/index.js"],
      "env": {
        "EMBEDDING_PROVIDER": "ollama", // default
        "EMBEDDING_MODEL": "nomic-embed-text", // optional
        "OPENAI_API_KEY": "your-api-key-here", // required for fallback
        "FALLBACK_PROVIDER": "openai", // recommended for reliability
        "FALLBACK_MODEL": "nomic-embed-text", // optional
        "QDRANT_URL": "http://localhost:6333"
      },
      "disabled": false,
      "autoApprove": [
        "search_documentation",
        "list_sources",
        "extract_urls",
        "remove_documentation",
        "list_queue",
        "run_queue",
        "clear_queue",
        "add_documentation",
        "add_repository",
        "list_repositories",
        "update_repository",
        "remove_repository",
        "watch_repository",
        "get_indexing_status"
      ]
    }
  }
}

{
  "mcpServers": {
    "rag-docs": {
      "command": "node",
      "args": ["/path/to/your/mcp-ragdocs/build/index.js"],
      "env": {
        "EMBEDDING_PROVIDER": "ollama", // default
        "EMBEDDING_MODEL": "nomic-embed-text", // optional
        "OPENAI_API_KEY": "your-api-key-here", // required for fallback
        "FALLBACK_PROVIDER": "openai", // recommended for reliability
        "FALLBACK_MODEL": "nomic-embed-text", // optional
        "QDRANT_URL": "http://localhost:6333"
      },
      "autoApprove": [
        "search_documentation",
        "list_sources",
        "extract_urls",
        "remove_documentation",
        "list_queue",
        "run_queue",
        "clear_queue",
        "add_documentation",
        "add_repository",
        "list_repositories",
        "update_repository",
        "remove_repository",
        "watch_repository",
        "get_indexing_status"
      ]
    }
  }
}

{
     // Ollama is used by default, no need to specify EMBEDDING_PROVIDER
     "EMBEDDING_MODEL": "nomic-embed-text", // optional
     "FALLBACK_PROVIDER": "openai",
     "FALLBACK_MODEL": "text-embedding-3-small",
     "OPENAI_API_KEY": "your-api-key-here"
   }

add_repository with {
  "path": "/path/to/your/repo",
  "name": "my-project",
  "include": ["**/*.js", "**/*.ts", "**/*.md"],
  "exclude": ["**/node_modules/**", "**/dist/**"],
  "watchMode": true
}

get_indexing_status with {
  "name": "my-project"
}

Repository: my-project
Status: 🔄 Processing
Progress: 45%
Started: 5/11/2025, 2:45:30 PM
Duration: 3m 15s
Files: 120 processed, 15 skipped (of 250)
Chunks: 1500 indexed (of 3300)
Batch: 15 of 33

{
  "repositories": [
    {
      "path": "/path/to/your/repo",

The configuration file is automatically updated when repositories are added, updated, or removed using the repository management tools. You can also manually edit the file to configure repositories before starting the server.

**Configuration Options:**

- `repositories`: Array of repository configurations
  - `path`: Absolute path to the repository directory
  - `name`: Unique name for the repository
  - `include`: Array of glob patterns to include
  - `exclude`: Array of glob patterns to exclude
  - `watchMode`: Whether to watch for changes
  - `watchInterval`: Polling interval in milliseconds
  - `chunkSize`: Default chunk size for files
  - `fileTypeConfig`: Configuration for specific file types
    - `include`: Whether to include this file type
    - `chunkStrategy`: Chunking strategy ("semantic", "line", or "character")
    - `chunkSize`: Optional override for chunk size

- `autoWatch`: Whether to automatically start watching repositories with `watchMode: true` at startup

## Acknowledgments

This project is a fork of [qpd-v/mcp-ragdocs](https://github.com/qpd-v/mcp-ragdocs), originally developed by qpd-v. The original project provided the foundation for this implementation.

Special thanks to the original creator, qpd-v, for their innovative work on the initial version of this MCP server. This fork has been enhanced with additional features and improvements by Rahul Retnan.

## Troubleshooting

### Server Not Starting (Port Conflict)

If the MCP server fails to start due to a port conflict, follow these steps:

1. Identify and kill the process using port 3030:

2. Restart the MCP server

3. If the issue persists, check for other processes using the port:

4. You can also change the default port in the configuration if needed

### Missing Tools in Claude Desktop

If certain tools (like `add_documentation`) are not appearing in Claude Desktop:

1. Verify that the tool is properly registered in the server's `handler-registry.ts` file
2. Make sure the tool is included in the `ListToolsRequestSchema` handler response
3. Check that your Claude Desktop configuration includes the tool in the `autoApprove` array
4. Restart the Claude Desktop application and the MCP server
5. Check the server logs for any errors related to tool registration

The most common cause of missing tools is that they are registered as handlers but not included in the `tools` array returned by the `ListToolsRequestSchema` handler.

### Timeout Issues with Large Repositories

If you encounter timeout errors when indexing large repositories:

1. The system now uses asynchronous processing to avoid MCP timeouts
2. When adding a repository with `add_repository`, the indexing will continue in the background
3. Use the `get_indexing_status` tool to monitor progress
4. If you still experience issues, try these solutions:
   - Reduce the scope of indexing with more specific include/exclude patterns
   - Break up very large repositories into smaller logical units
   - Increase the batch size in the code if your system has more resources available
   - Check system resources (memory, CPU) during indexing to identify bottlenecks