💸 FinancialAssistant

by nielsenfonseca

315 downloads

Not rated

GitHub

Other

About

Financial MultiAgent Colaboration with MCP Server with Tools

Details

Author: nielsenfonseca
Downloads: 315
Categories: Other

- Four specialized agents: Generic, Emergency Fund, Savings, and Investment.
- LLM-powered router detects user intent and directs to the correct agent.
- Conversational graph (LangGraph) maintains multi‑turn dialogue.
- External API tools calculate monthly expenses, ideal reserve, savings capacity, and investment suggestions.
- Google Gemini used as the underlying LLM (via langchain_google_genai).
- Empathetic, human‑friendly explanation of all financial calculations.

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 💸 FinancialAssistant

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": {
        "\ud83d\udcb8 financialassistant": {
            "FinancialAssistant": {
                "command": "python",
                "args": [
                    "-m",
                    "venv",
                    "venv"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "\ud83d\udcb8 financialassistant": {
            "FinancialAssistant": {
                "command": "python",
                "args": [
                    "-m",
                    "venv",
                    "venv"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "\ud83d\udcb8 financialassistant": {
            "FinancialAssistant": {
                "command": "python",
                "args": [
                    "-m",
                    "venv",
                    "venv"
                ]
            }
        }
    }
}

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": {
        "\ud83d\udcb8 financialassistant": {
            "FinancialAssistant": {
                "command": "python",
                "args": [
                    "-m",
                    "venv",
                    "venv"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "\ud83d\udcb8 financialassistant": {
            "FinancialAssistant": {
                "command": "python",
                "args": [
                    "-m",
                    "venv",
                    "venv"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "\ud83d\udcb8 financialassistant": {
            "FinancialAssistant": {
                "command": "python",
                "args": [
                    "-m",
                    "venv",
                    "venv"
                ]
            }
        }
    }
}

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": {
        "\ud83d\udcb8 financialassistant": {
            "FinancialAssistant": {
                "command": "python",
                "args": [
                    "-m",
                    "venv",
                    "venv"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "\ud83d\udcb8 financialassistant": {
            "FinancialAssistant": {
                "command": "python",
                "args": [
                    "-m",
                    "venv",
                    "venv"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "\ud83d\udcb8 financialassistant": {
            "FinancialAssistant": {
                "command": "python",
                "args": [
                    "-m",
                    "venv",
                    "venv"
                ]
            }
        }
    }
}

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": {
        "\ud83d\udcb8 financialassistant": {
            "FinancialAssistant": {
                "command": "python",
                "args": [
                    "-m",
                    "venv",
                    "venv"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "\ud83d\udcb8 financialassistant": {
            "FinancialAssistant": {
                "command": "python",
                "args": [
                    "-m",
                    "venv",
                    "venv"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "\ud83d\udcb8 financialassistant": {
            "FinancialAssistant": {
                "command": "python",
                "args": [
                    "-m",
                    "venv",
                    "venv"
                ]
            }
        }
    }
}

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": {
        "\ud83d\udcb8 financialassistant": {
            "FinancialAssistant": {
                "command": "python",
                "args": [
                    "-m",
                    "venv",
                    "venv"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "\ud83d\udcb8 financialassistant": {
            "FinancialAssistant": {
                "command": "python",
                "args": [
                    "-m",
                    "venv",
                    "venv"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "\ud83d\udcb8 financialassistant": {
            "FinancialAssistant": {
                "command": "python",
                "args": [
                    "-m",
                    "venv",
                    "venv"
                ]
            }
        }
    }
}

From the repository

Clone the repository, create a Python 3.10+ virtual environment, install dependencies with pip install -r requirements.txt, set the GOOGLE_API_KEY and MCP_SERVER_URL in a .env file, then run python main.py to start the assistant.

Claude Desktop / Cursor

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

{
    "mcpServers": {
        "\ud83d\udcb8 financialassistant": {
            "FinancialAssistant": {
                "command": "python",
                "args": [
                    "-m",
                    "venv",
                    "venv"
                ]
            }
        }
    }
}

McpServers

{
    "FinancialAssistant": {
        "command": "python",
        "args": [
            "-m",
            "venv",
            "venv"
        ]
    }
}

💸 FinancialAssistant

O FinancialAssistant é um assistente financeiro inteligente que utiliza LLMs (Modelos de Linguagem) e uma arquitetura modular baseada em agentes para ajudar usuários a:

- 📊 Calcular sua reserva de emergência
- 💰 Avaliar sua capacidade de poupança
- 📈 Obter sugestões de investimento
- 🤝 Conversar sobre educação financeira em geral

Ele integra ferramentas externas (APIs) para cálculos e simulações financeiras, e usa o LLM para explicar as respostas de forma humana, empática e personalizada.

---

🚀 Tecnologias utilizadas

- Python 3.10+
- LangGraph
- LangChain
- Google Gemini (via langchain_google_genai)
- Requests
- .env + dotenv

---

🧠 Arquitetura

O projeto é composto por:

1. Agentes Especializados (pasta `agents/`)

Cada agente é responsável por um tipo de assistência:

- GenericAgent → inicia conversas gerais e educacionais
- EmergencyFundAgent → ajuda a montar uma reserva de emergência
- SavingsAgent → analisa sua capacidade de poupar mensalmente
- InvestmentAgent → sugere investimentos com base em seu perfil

Todos usam LLMs para explicar o resultado das ferramentas de forma clara e empática.

2. Grafo conversacional (LangGraph)

- Um roteador com LLM detecta a intenção do usuário e direciona para o agente certo - Cada agente pode manter o controle da conversa por múltiplas mensagens, usando state["intencao_pendente"]

3. Ferramentas externas (API)

APIs externas realizam os cálculos de: - Gasto médio mensal - Valor ideal de reserva de emergência - Capacidade de poupança - Sugestões de investimento

---

🛠 Como rodar o projeto localmente

```bash

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.

💸 FinancialAssistant

About

Details

Jump to

Setting up with Highlight

Setting up with Cursor

JSON

JSON

JSON

Setting up with Claude Desktop

JSON

JSON

JSON

Setting up with Windsurf

JSON

JSON

JSON

Setting up with Cline

JSON

JSON

JSON

Setting up with Goose

JSON

JSON

JSON

From the repository

Claude Desktop / Cursor

McpServers

💸 FinancialAssistant

🚀 Tecnologias utilizadas

🧠 Arquitetura

1. Agentes Especializados (pasta `agents/`)

2. Grafo conversacional (LangGraph)

3. Ferramentas externas (API)

🛠 Como rodar o projeto localmente

Install

About

Details

Jump to

Setting up with Highlight

From the repository

Claude Desktop / Cursor

McpServers

💸 FinancialAssistant

🚀 Tecnologias utilizadas

🧠 Arquitetura

1. Agentes Especializados (pasta agents/)

2. Grafo conversacional (LangGraph)

3. Ferramentas externas (API)

🛠 Como rodar o projeto localmente

Install

More like this

Sequential Thinking

Filesystem

EverArt

Google Drive

Reactive Resume

FastMCP v2 🚀

1. Agentes Especializados (pasta `agents/`)