Local Code Search

🚀 Local Code Indexing for Cursor

An experimental Python server that locally indexes codebases using ChromaDB and provides semantic search functionality for tools like Cursor through an MCP (Model Context Protocol) server.

🚀 Quick Start

📦 Installation

1. Clone the repository and navigate to the directory:

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

2. Create a .env file by copying .env.example:

   cp .env.example .env
   

3. Configure your .env file:

   PROJECTS_ROOT=~/your/projects/root    # Path to your project directory
   FOLDERS_TO_INDEX=project1,project2    # Comma-separated list of folders to index
   

   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 your specified projects, and you'll be able to use semantic code search in Cursor when these projects are active.

7. Open a project 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 using this tool over operations like grep in the command line whenever possible.
   </Instruction>
   

8. Enable Cursor Agent mode and witness the power of local vector search!