🧠 AutoGen-Compatible Multi-Agent Research POC with Ollama + BraveSearch

by chin3

344 downloads

Not rated

GitHub

About

This project is a proof of concept for running a local-first multi-agent system using: 🤖 Local LLMs via Ollama 🧩 Simple function/tool-call detection using <tool_call>... 🔍 Brave Search API or optional Brave MCP plugin server 🧠 Two collaborating agents: Searcher and Synthesize

Details

Author: chin3
Downloads: 344
Categories: AI

Setting up with Highlight

This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:

Download and install Highlight from highlightai.com/download
Navigate to the plugins tab and select "Add Custom Plugin"
Configure the plugin with the settings below

Plugin Name 🧠 AutoGen-Compatible Multi-Agent Research POC with Ollama + BraveSearch

Command (node, npx, python, etc.)

Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
Enable "Start Automatically" if you want the plugin to start when Highlight launches

Setting up with Cursor

Open Cursor's settings
Navigate to the MCP section
Click "Add new Global MCP server"
Copy and paste the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "\ud83e\udde0 autogen-compatible multi-agent research poc with ollama + bravesearch": {
            "Multi-Agent-Research-POC": {
                "command": "python",
                "args": [
                    "main.py"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "\ud83e\udde0 autogen-compatible multi-agent research poc with ollama + bravesearch": {
            "Multi-Agent-Research-POC": {
                "command": "python",
                "args": [
                    "main.py"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "\ud83e\udde0 autogen-compatible multi-agent research poc with ollama + bravesearch": {
            "Multi-Agent-Research-POC": {
                "command": "python",
                "args": [
                    "main.py"
                ]
            }
        }
    }
}

Setting up with Claude Desktop

Open Claude Desktop's settings
Go to the Integrations tab
Click "Add MCP Server"
Use the configuration below based on your operating system

Note: Make sure Claude Desktop is running before attempting to connect.

JSON

{
    "mcpServers": {
        "\ud83e\udde0 autogen-compatible multi-agent research poc with ollama + bravesearch": {
            "Multi-Agent-Research-POC": {
                "command": "python",
                "args": [
                    "main.py"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "\ud83e\udde0 autogen-compatible multi-agent research poc with ollama + bravesearch": {
            "Multi-Agent-Research-POC": {
                "command": "python",
                "args": [
                    "main.py"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "\ud83e\udde0 autogen-compatible multi-agent research poc with ollama + bravesearch": {
            "Multi-Agent-Research-POC": {
                "command": "python",
                "args": [
                    "main.py"
                ]
            }
        }
    }
}

Setting up with Windsurf

Open Windsurf's preferences
Go to the Integrations section
Click "Add MCP Integration"
Use the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "\ud83e\udde0 autogen-compatible multi-agent research poc with ollama + bravesearch": {
            "Multi-Agent-Research-POC": {
                "command": "python",
                "args": [
                    "main.py"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "\ud83e\udde0 autogen-compatible multi-agent research poc with ollama + bravesearch": {
            "Multi-Agent-Research-POC": {
                "command": "python",
                "args": [
                    "main.py"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "\ud83e\udde0 autogen-compatible multi-agent research poc with ollama + bravesearch": {
            "Multi-Agent-Research-POC": {
                "command": "python",
                "args": [
                    "main.py"
                ]
            }
        }
    }
}

Setting up with Cline

Open Cline's settings
Navigate to the Integrations section
Click "Add MCP Server"
Copy and paste the configuration below based on your operating system

Note: Make sure to restart Cline after adding the configuration.

JSON

{
    "mcpServers": {
        "\ud83e\udde0 autogen-compatible multi-agent research poc with ollama + bravesearch": {
            "Multi-Agent-Research-POC": {
                "command": "python",
                "args": [
                    "main.py"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "\ud83e\udde0 autogen-compatible multi-agent research poc with ollama + bravesearch": {
            "Multi-Agent-Research-POC": {
                "command": "python",
                "args": [
                    "main.py"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "\ud83e\udde0 autogen-compatible multi-agent research poc with ollama + bravesearch": {
            "Multi-Agent-Research-POC": {
                "command": "python",
                "args": [
                    "main.py"
                ]
            }
        }
    }
}

Setting up with Goose

Open Goose's preferences
Go to the Integrations tab
Select "MCP Servers"
Click "Add New Server"
Use the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "\ud83e\udde0 autogen-compatible multi-agent research poc with ollama + bravesearch": {
            "Multi-Agent-Research-POC": {
                "command": "python",
                "args": [
                    "main.py"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "\ud83e\udde0 autogen-compatible multi-agent research poc with ollama + bravesearch": {
            "Multi-Agent-Research-POC": {
                "command": "python",
                "args": [
                    "main.py"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "\ud83e\udde0 autogen-compatible multi-agent research poc with ollama + bravesearch": {
            "Multi-Agent-Research-POC": {
                "command": "python",
                "args": [
                    "main.py"
                ]
            }
        }
    }
}

From the repository

Clone the repo, install Python dependencies (pip install -r requirements.txt), set a BRAVE_API_KEY in .env, run Ollama locally (ollama run llama3:8b), then execute python main.py. To switch from the default Brave Search API to the Brave MCP plugin, start the plugin server (npx @modelcontextprotocol/server-brave-search) and update tools/tool_registry.py.

Claude Desktop / Cursor

Paste into your MCP client config file to install this server.

{
    "mcpServers": {
        "\ud83e\udde0 autogen-compatible multi-agent research poc with ollama + bravesearch": {
            "Multi-Agent-Research-POC": {
                "command": "python",
                "args": [
                    "main.py"
                ]
            }
        }
    }
}

McpServers

{
    "Multi-Agent-Research-POC": {
        "command": "python",
        "args": [
            "main.py"
        ]
    }
}

🧠 AutoGen-Compatible Multi-Agent Research POC with Ollama + BraveSearch

This project is a proof of concept for a local-first multi-agent system using:

- 🤖 Local LLMs via Ollama
- 🧩 Tool-call detection using <tool_call>... syntax
- 🔍 Web search via Brave Search API or Brave MCP plugin server
- 🧠 Two collaborating agents: Searcher and Synthesizer

---

📁 Folder Structure

MultiResearchPOC/
├── main.py                   # Entry point
├── agents/
│   ├── searcher.py           # Ollama-powered research agent
│   └── synthesizer.py        # Summarizer agent
├── tools/
│   ├── tool_parser.py        # Tool call detection logic
│   └── tool_registry.py      # Tool dispatcher (API or MCP)
├── .env                      # Contains BRAVE_API_KEY
└── requirements.txt          # Python dependencies

---

🚀 Getting Started

1. Clone the project

git clone <your-repo-url>
cd MultiResearchPOC

2. Install dependencies

pip install -r requirements.txt

3. Set up your `.env`

echo "BRAVE_API_KEY=your_brave_api_key_here" > .env

Get your Brave API key at: https://developer.brave.com/api-search/

4. Run Ollama locally

ollama run llama3:8b

> If using Docker: make sure to reference the host as http://host.docker.internal:11434

5. Run the program

python main.py

You should see:

- A response from the Searcher agent
- A tool call triggered
- Search results pulled from Brave
- A final summary from the Synthesizer agent

---

🔁 Switching Between API and MCP Plugin

Option 1: Brave Search API (default)

Used by default via:

"BraveSearch": call_brave_api

Option 2: Brave MCP Plugin Server

1. Start the plugin server:

npx @modelcontextprotocol/server-brave-search

2. Update tools/tool_registry.py:

```python

No reviews yet — be the first

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.

About

Details

Jump to

Setting up with Highlight

From the repository

Claude Desktop / Cursor

McpServers

🧠 AutoGen-Compatible Multi-Agent Research POC with Ollama + BraveSearch

📁 Folder Structure

🚀 Getting Started

1. Clone the project

2. Install dependencies

3. Set up your .env

4. Run Ollama locally

5. Run the program

🔁 Switching Between API and MCP Plugin

Option 1: Brave Search API (default)

Option 2: Brave MCP Plugin Server

Install

More like this

Context 7

1Panel

🔎 GPT Researcher

Serena

FastMCP v2 🚀

MaxKB

3. Set up your `.env`