Ollama Deep Researcher MCP server for AI agents

The Ollama Deep Researcher DXT Extension is a powerful tool that enables advanced topic research by combining web search capabilities with LLM synthesis. This extension works as an MCP server that integrates with the Desktop Extension (DXT) ecosystem, allowing you to research any topic using web search APIs and locally running language models.

Installation

To set up the Ollama Deep Researcher, follow these steps:

Clone the repository and install Node.js dependencies:

git clone <your-repo-url>
cd mcp-server-ollama-deep-researcher
npm install

Install Python dependencies:

cd src/assistant
pip install -r requirements.txt

Configure API keys for web search functionality by setting the following environment variables:
```
export TAVILY_API_KEY=your_tavily_key
export PERPLEXITY_API_KEY=your_perplexity_key
```
Build the TypeScript server:
```
npm run build
```
Run the extension:
```
node dist/index.js
```

Using the Ollama Deep Researcher

Research a Topic

To start researching a topic, use the research tool with a topic parameter:

{
  "topic": "Your research subject"
}

The server will initiate the research process, using web search APIs and LLMs to gather and synthesize information about your topic.

Check Research Status

You can monitor the progress of your research by using the get_status tool, which will return the current state of your research process.

Configure Research Parameters

Customize your research experience by adjusting the parameters with the configure tool:

{
  "maxLoops": 5,
  "llmModel": "llama3",
  "searchApi": "tavily"
}

Available configuration options:

maxLoops: Maximum number of research iterations
llmModel: The LLM model to use (Ollama, DeepSeek, etc.)
searchApi: Web search API provider (Tavily or Perplexity)

Troubleshooting

If you encounter issues while using the extension, consider these common problems:

API Key Issues: Ensure that TAVILY_API_KEY or PERPLEXITY_API_KEY environment variables are properly set
Python Errors: Check stderr for Python dependency issues or runtime errors
Research Timeouts: Note that research processes automatically terminate after 5 minutes to prevent hangs

The server logs to stderr, which can help diagnose any problems that occur during operation.

How to install this MCP server

For Claude Code

To add this MCP server to Claude Code, run this command in your terminal:

claude mcp add-json "ollama-deep-researcher" '{"command":"node","args":["path/to/mcp-server-ollama-deep-researcher/build/index.js"],"env":{"LANGSMITH_TRACING":"true","LANGSMITH_ENDPOINT":"https://api.smith.langchain.com","LANGSMITH_API_KEY":"your-langsmith-key","LANGSMITH_PROJECT":"ollama-deep-researcher-mcp-server","TAVILY_API_KEY":"your-tavily-key","PERPLEXITY_API_KEY":"your-perplexity-key","PYTHONPATH":"path/to/mcp-server-ollama-deep-researcher/src"}}'

See the official Claude Code MCP documentation for more details.

For Cursor

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.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "ollama-deep-researcher": {
            "command": "node",
            "args": [
                "path/to/mcp-server-ollama-deep-researcher/build/index.js"
            ],
            "env": {
                "LANGSMITH_TRACING": "true",
                "LANGSMITH_ENDPOINT": "https://api.smith.langchain.com",
                "LANGSMITH_API_KEY": "your-langsmith-key",
                "LANGSMITH_PROJECT": "ollama-deep-researcher-mcp-server",
                "TAVILY_API_KEY": "your-tavily-key",
                "PERPLEXITY_API_KEY": "your-perplexity-key",
                "PYTHONPATH": "path/to/mcp-server-ollama-deep-researcher/src"
            }
        }
    }
}

Adding an MCP server to a project

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.

How to use the MCP server

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 explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.

For Claude Desktop

To add this MCP server to Claude Desktop:

1. Find your configuration file:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
Linux: ~/.config/Claude/claude_desktop_config.json

2. Add this to your configuration file:

{
    "mcpServers": {
        "ollama-deep-researcher": {
            "command": "node",
            "args": [
                "path/to/mcp-server-ollama-deep-researcher/build/index.js"
            ],
            "env": {
                "LANGSMITH_TRACING": "true",
                "LANGSMITH_ENDPOINT": "https://api.smith.langchain.com",
                "LANGSMITH_API_KEY": "your-langsmith-key",
                "LANGSMITH_PROJECT": "ollama-deep-researcher-mcp-server",
                "TAVILY_API_KEY": "your-tavily-key",
                "PERPLEXITY_API_KEY": "your-perplexity-key",
                "PYTHONPATH": "path/to/mcp-server-ollama-deep-researcher/src"
            }
        }
    }
}

3. Restart Claude Desktop for the changes to take effect