Deep Research MCP Server

What does “Deep Research” MCP Server do?

The Deep Research MCP Server is designed to facilitate comprehensive research on complex topics by leveraging AI capabilities to streamline the research process. Acting as a bridge between AI assistants and external data sources, it automates the exploration of research questions, the identification of key concepts, and the generation of structured, well-cited reports. The server integrates web search, content analysis, and report synthesis, assisting users in elaborating questions, generating subquestions, collecting relevant resources, and producing evidence-based conclusions. Its primary role is to empower developers and researchers to conduct in-depth investigations, surface authoritative sources, and automate the workflow of assembling and presenting research findings.

List of Prompts

• deep-research: Tailored for comprehensive research tasks with a structured approach.

List of Resources

No explicit resources are described in the available documentation or repository files.

List of Tools

No explicit tools are listed in the available repository files, including server.py or equivalent.

Use Cases of this MCP Server

• Academic Research Assistance: Automates the process of elaborating on research questions, generating subquestions, and synthesizing findings, saving time for students and academics.
• Market or Trend Analysis: Enables users to conduct structured investigations into markets or trends, gathering authoritative sources and presenting balanced reports.
• Technical Topic Summarization: Assists developers and professionals in breaking down technical topics into subquestions, organizing web search results, and producing comprehensive documentation.
• Content Creation Support: Provides writers and journalists with well-cited, evidence-based summaries on complex subjects for articles or reports.
• Decision Support: Helps decision-makers explore multiple perspectives and gather relevant data before drawing conclusions on important matters.

How to set it up

Windsurf

1. Ensure prerequisites such as Node.js and uv/uvx are installed.
2. Locate your Windsurf configuration file.
3. Add the Deep Research MCP Server to the mcpServers object with the following snippet:

   "mcpServers": {
     "mcp-server-deep-research": {
       "command": "uvx",
       "args": [
         "--directory",
         "/path/to/mcp-server-deep-research",
         "run",
         "mcp-server-deep-research"
       ]
     }
   }
   

4. Save the configuration and restart Windsurf.
5. Verify the server is running and accessible.

Claude

1. Download and install Claude Desktop from here.
2. On macOS, run:

   python setup.py
   

3. Locate your Claude configuration file:
   • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
   • Windows: %APPDATA%/Claude/claude_desktop_config.json
4. Add or update your mcpServers configuration as follows:

   "mcpServers": {
     "mcp-server-deep-research": {
       "command": "uvx",
       "args": [
         "--directory",
         "/path/to/mcp-server-deep-research",
         "run",
         "mcp-server-deep-research"
       ]
     }
   }
   

5. Save the file and restart Claude.
6. Select the deep-research prompt template to begin.

Cursor

1. Ensure Node.js and uvx are installed.
2. Locate the Cursor MCP configuration file.
3. Add Deep Research MCP Server using:

   "mcpServers": {
     "mcp-server-deep-research": {
       "command": "uvx",
       "args": [
         "--directory",
         "/path/to/mcp-server-deep-research",
         "run",
         "mcp-server-deep-research"
       ]
     }
   }
   

4. Save the configuration and restart Cursor.
5. Confirm it is operational.

Cline

1. Make sure all dependencies (Node.js, uvx) are installed.
2. Find the Cline configuration file.
3. Insert the following MCP Server configuration:

   "mcpServers": {
     "mcp-server-deep-research": {
       "command": "uvx",
       "args": [
         "--directory",
         "/path/to/mcp-server-deep-research",
         "run",
         "mcp-server-deep-research"
       ]
     }
   }
   

4. Restart Cline after saving changes.
5. Verify server accessibility.

Securing API Keys

To secure API keys, use environment variables in your configuration. Example:

"mcpServers": {
  "mcp-server-deep-research": {
    "command": "uvx",
    "args": [
      "--directory",
      "/path/to/mcp-server-deep-research",
      "run",
      "mcp-server-deep-research"
    ],
    "env": {
      "API_KEY": "${API_KEY}"
    },
    "inputs": {
      "api_key": "${API_KEY}"
    }
  }
}

How to use this MCP inside flows

Using MCP in FlowHunt

To integrate MCP servers into your FlowHunt workflow, start by adding the MCP component to your flow and connecting it to your AI agent:

Click on the MCP component to open the configuration panel. In the system MCP configuration section, insert your MCP server details using this JSON format:

{
  "mcp-server-deep-research": {
    "transport": "streamable_http",
    "url": "https://yourmcpserver.example/pathtothemcp/url"
  }
}

Once configured, the AI agent is now able to use this MCP as a tool with access to all its functions and capabilities. Remember to change “mcp-server-deep-research” to whatever the actual name of your MCP server is and replace the URL with your own MCP server URL.

Overview

Our opinion

This MCP server provides clear documentation, a well-described workflow, and prompt templates but lacks explicit details on resources, tools, or advanced MCP features such as roots and sampling. The absence of detailed API or tool listings limits its flexibility for some advanced scenarios. Overall, it is practical for structured research workflows but less suited for highly customized integrations.

MCP Score