Cursor Local Indexing

🚀 Local Code Indexing Service with ChromaDB (for Cursor)

An experimental Python-based server that locally indexes codebases using ChromaDB and provides semantic search tools via an MCP (Model Context Protocol) server, suitable for IDEs like Cursor.

🚀 Quick Start

📦 Installation

1. Clone the repository and navigate to the directory:

   git clone <repository-url>
   cd cursor-local-indexing
   

2. Copy the .env.example file to create a .env file:

   cp .env.example .env
   

3. Configure the .env file:

   PROJECTS_ROOT=~/your/projects/root    # Path to the project directory
   FOLDERS_TO_INDEX=project1,project2    # List of folders to index (comma-separated)
   

   Example:

   PROJECTS_ROOT=~/projects
   FOLDERS_TO_INDEX=project1,project2
   

4. Start the indexing server:

   docker-compose up -d
   

5. Configure Cursor to use the local search server: Create or edit the ~/.cursor/mcp.json file:

   {
     "mcpServers": {
       "workspace-code-search": {
         "url": "http://localhost:8978/sse"
       }
     }
   }
   

6. Restart the Cursor IDE to apply the changes. The server will start indexing the projects you specified, and you'll be able to use semantic code search in Cursor when these projects are active.

7. Open any of the projects configured for indexing. Create a .cursorrules file and add the following content:

<Instruction>
For any request, first use the @search_code tool to check the functionality of the code.
Prioritize this before turning to tools like command-line grep.
</Instruction>

8. Enable Cursor Agent mode to see the effects of local vector search!