OpenDeepSearch is a powerful research tool that combines structured thinking with Brave Search capabilities to provide comprehensive, well-sourced research reports on complex topics. It integrates with Model Context Protocol (MCP) clients like Claude Desktop and Cursor to deliver detailed analysis and synthesis of information.
npm install -g open-deep-research
BRAVE_API_KEY=your_api_key npx open-deep-research
# Clone the repository
git clone https://github.com/tositon/open-deep-research.git
cd open-deep-research
# Install dependencies
npm install
# Build the project
npm run build
# Run with Brave Search API
BRAVE_API_KEY=your_api_key npm start
# Install for Claude
npx @smithery/cli install open-deep-research --client claude
# Install for Cursor
npx @smithery/cli install open-deep-research --client cursor
During Smithery installation, you'll be prompted to enter your Brave Search API key.
Add the following to your Claude Desktop configuration:
{
"mcpServers": {
"open-deep-research": {
"command": "npx",
"args": [
"-y",
"open-deep-research"
],
"env": {
"BRAVE_API_KEY": "your_api_key_here"
}
}
}
}
In Cursor, add the MCP server with:
claude mcp add "open-deep-research" npx open-deep-research
Make sure to set the BRAVE_API_KEY
environment variable before running Cursor.
You can ask complex research questions such as:
OpenDeepSearch processes your research queries through several stages:
For testing the MCP server, you can use MCP Inspector:
# Install and run MCP Inspector
npx @modelcontextprotocol/inspector
# Run the server in another terminal
BRAVE_API_KEY=your_api_key npm start
After launching Inspector, open your browser and go to http://localhost:5173. Connect to the WebSocket server using the URL ws://localhost:3000
.
In the MCP Inspector interface, you can select a tool and configure request parameters:
{
"query": "latest quantum computing advancements",
"count": 5
}
{
"thought": "Starting analysis of global warming problem",
"thoughtNumber": 1,
"totalThoughts": 5,
"nextThoughtNeeded": true
}
{
"query": "Comparison of different renewable energy sources",
"action": "start",
"maxSubQuestions": 3
}
There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json
file so that it is available in all of your projects.
If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json
file.
To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".
When you click that button the ~/.cursor/mcp.json
file will be opened and you can add your server like this:
{
"mcpServers": {
"cursor-rules-mcp": {
"command": "npx",
"args": [
"-y",
"cursor-rules-mcp"
]
}
}
}
To add an MCP server to a project you can create a new .cursor/mcp.json
file or add it to the existing one. This will look exactly the same as the global MCP server example above.
Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.
The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.
You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.