Qonto MCP Server

Qonto MCP Server

Enables AI assistants to access Qonto financial data including organization info, account balances, transaction history, and business operations through natural language.

Category
Visit Server

README

<div align="center">

💸 Qonto Local MCP Server 🤖

</div>

<div align="center">

Python 3.10+ Build Status Platform AI Powered

</div>

🌐 Usage

https://github.com/user-attachments/assets/619cd6a1-e064-4518-a84c-8134c09fae03

[!IMPORTANT] Security and customer trust are fundamental to everything we do at Qonto. While this repository enables powerful innovation and integration capabilities, it's important to understand that certain risks are inherent to the use of the MCP technology itself. Please review the following security information carefully.

⚠️🔒 SECURITY NOTICE

The MCP (Model Context Provider) protocol gives AI models access to additional functionality like reading files, accessing APIs, and generate responses based on contextual data.

While this brings powerful integration capabilities, it also introduces important security considerations.

A malicious MCP server can secretly steal credentials and maliciously exploit other trusted MCP servers you're using (read more).

These risks are not specific to Qonto’s MCP server, but apply to any use of the MCP protocol.

We recommend to only use MCP servers you trust, just as you would with any software you install on your computer.

Questions or security concerns? Contact us at security@qonto.com.

Getting started

  1. Install Claude Desktop
  2. Get your organization ID and API key from your Qonto account's /settings/integrations section:

image

Option 1: Docker Installation (Recommended)

  1. Pull the Docker image:
    docker pull qonto/qonto-mcp-server:latest
    
  2. In your Claude Desktop claude_desktop_config.json file, add the Qonto MCP server as follows:
{
  "mcpServers": {
    "Qonto MCP Docker": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "-e", "QONTO_API_KEY=<QONTO_API_KEY>",                 // <- change this with the API key from the settings page
        "-e", "QONTO_ORGANIZATION_ID=<QONTO_ORGANIZATION_ID>", // <- change this with the organization id from the settings page
        "-e", "QONTO_THIRDPARTY_HOST=https://thirdparty.qonto.com",
        "qonto/qonto-mcp-server:latest"
      ]
    }
  }
}

For example, this is a full Docker configuration:

{
  "mcpServers": {
    "Qonto MCP Docker": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "-e", "QONTO_API_KEY=abcdefghihlmnopqrstuvxz123456",
        "-e", "QONTO_ORGANIZATION_ID=qonto-organization-slug-1234",
        "-e", "QONTO_THIRDPARTY_HOST=https://thirdparty.qonto.com",
        "qonto/qonto-mcp-server:latest"
      ]
    }
  }
}

<details> <summary>Option 2: Local Installation</summary>

  1. Clone this repository locally
  2. Install uv. If you're on Mac, you can just do brew install uv
  3. In your Claude Desktop claude_desktop_config.json file, add the Qonto MCP server as follows:

Note: You can optionally pass --transport streamable-http to use HTTP transport instead of the default stdio transport protocol.

{
  "mcpServers": {
    "Qonto MCP": {
      "command": "uv",
      "args": [
        "run",
        "--with",
        "mcp[cli]",
        "--with",
        "requests",
        "mcp",
        "run",
        "<PATH_TO_CLONED_REPO_FOLDER, ie. ~/development/qonto-mcp/qonto_mcp/server.py>", // <- change this
        "--transport",
        "stdio"  // <- optional: change to "streamable-http" for HTTP transport
      ],
      "env": {
        "QONTO_API_KEY": "<QONTO_API_KEY>",                 // <- change this with the API key from the settings page
        "QONTO_ORGANIZATION_ID": "<QONTO_ORGANIZATION_ID>", // <- change this with the organization id from the settings page
        "QONTO_THIRDPARTY_HOST": "https://thirdparty.qonto.com",
        "PYTHONPATH": "<PATH_TO_CLONED_REPO, ie. ~/development/qonto-mcp>" // <- change this
      }
    }
  }
}

For example, this is a full configuration:

{
  "mcpServers": {
    "Qonto MCP": {
      "command": "uv",
      "args": [
        "run",
        "--with",
        "mcp[cli]",
        "--with",
        "requests",
        "mcp",
        "run",
        "~/development/qonto-mcp/qonto_mcp/server.py",
        "--transport",
        "stdio"
      ],
      "env": {
        "QONTO_API_KEY": "abcdefghihlmnopqrstuvxz123456",
        "QONTO_ORGANIZATION_ID": "qonto-organization-slug-1234",
        "QONTO_THIRDPARTY_HOST": "https://thirdparty.qonto.com",
        "PYTHONPATH": "~/development/qonto-mcp"
      }
    }
  }
}

</details>

Available Tools

This MCP server provides the following tools for interacting with your Qonto account:

  • Organization Info: Get details about your Qonto organization
  • Account Management: Access account information and balances
  • Transaction History: Retrieve and analyze transaction data
  • Business Operations: Access business-related financial data

Configuration

Environment Variables

  • QONTO_API_KEY: Your Qonto API key (required)
  • QONTO_ORGANIZATION_ID: Your organization ID (required)
  • QONTO_THIRDPARTY_HOST: API host URL (defaults to https://thirdparty.qonto.com)

Transport Options

The server supports both stdio and streamable-http transport protocols. Use stdio for most cases, or streamable-http if you need HTTP-based communication.

Troubleshooting

Common Issues

  1. Invalid API credentials: Ensure your API key and organization ID are correct
  2. Connection timeout: Check your network connection and API host URL
  3. Claude Desktop not recognizing the server: Restart Claude Desktop after configuration changes

Contributing

Contributions are welcome! Please feel free to submit issues and enhancement requests.

License

This project is licensed under the MIT License - see the LICENSE file for details.

Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official
Featured
TypeScript
Kagi MCP Server

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured