qonto
Qonto MCP Server
claude mcp add --transport stdio qonto-qonto-mcp-server uv run --with mcp[cli] --with requests mcp run <PATH_TO_CLONED_REPO_FOLDER/qonto_mcp/server.py> --transport stdio \ --env PYTHONPATH="<PATH_TO_CLONED_REPO_FOLDER>" \ --env QONTO_API_KEY="<QONTO_API_KEY>" \ --env QONTO_ORGANIZATION_ID="<QONTO_ORGANIZATION_ID>" \ --env QONTO_THIRDPARTY_HOST="https://thirdparty.qonto.com"
How to use
This MCP server provides programmatic access to Qonto account data via the MCP (Model Context Protocol). It exposes tools for retrieving organization details, managing accounts and balances, and querying transaction history, as well as business-related financial data. You can run it either via Docker using the official image or locally with UV (Python) by pointing the MCP client to the server script. Once configured in Claude Desktop or your MCP client, you can invoke the available tools like Organization Info, Account Management, Transaction History, and Business Operations to integrate Qonto data into AI workflows or automated processes.
How to install
Prerequisites:\n- Docker (for Docker deployment) or Python 3.10+ with uv (for local deployment)\n- Claude Desktop or an MCP client configured to load mcpServers\n- Your Qonto API credentials (API key and organization ID) and the third-party host if needed\n\nInstall and run (Docker):\n1) Ensure Docker is installed and running.\n2) Pull the Qonto MCP server image:\n docker pull qonto/qonto-mcp-server:latest\n3) Configure your Claude Desktop or MCP client by adding the server entry (see mcp_config example above) and provide the required environment variables.\n4) Start using the Qonto MCP server through the MCP client.\n\nInstall and run (Local with uv):\n1) Ensure Python 3.10+ and uv are installed. If uv is not installed, install it: pip install uv\n2) Clone this repository locally.\n3) In your Claude Desktop or MCP client configuration, add the local Qonto MCP server entry. The command will look like:\n uv run --with mcp[cli] --with requests mcp run <PATH_TO_CLONED_REPO_FOLDER/qonto_mcp/server.py> --transport stdio\n4) Set the required environment variables (QONTO_API_KEY, QONTO_ORGANIZATION_ID, QONTO_THIRDPARTY_HOST, PYTHONPATH) as shown in the example config.\n5) Start using the MCP server.
Additional notes
Security: This MCP server interacts with sensitive financial data. Use only trusted MCP servers and keep API credentials secure. Transport options include stdio (default) or streamable-http for HTTP-based communication. Environment variables (QONTO_API_KEY, QONTO_ORGANIZATION_ID, QONTO_THIRDPARTY_HOST) must be provided for proper operation. If Claude Desktop does not recognize the server after changes, restart the application. If using Docker, ensure the API key and organization ID are supplied as environment variables within the container. For local development, ensure PYTHONPATH points to the repository root where qonto_mcp exists. The available tools include Organization Info, Account Management, Transaction History, and Business Operations.
Related MCP Servers
PPTAgent
An Agentic Framework for Reflective PowerPoint Generation
mcp-redis
The official Redis MCP Server is a natural language interface designed for agentic applications to manage and search data in Redis efficiently
TradingAgents mode
TradingAgents-MCPmode 是一个创新的多智能体交易分析系统,集成了 Model Context Protocol (MCP) 工具,实现了智能化的股票分析和交易决策流程。系统通过多个专业化智能体的协作,提供全面的市场分析、投资建议和风险管理。
sec-edgar
A SEC EDGAR MCP (Model Context Protocol) Server
mcp -odoo
A Model Context Protocol (MCP) server that enables AI assistants to securely interact with Odoo ERP systems through standardized resources and tools for data retrieval and manipulation.
metatrader
Model Context Protocol (MCP) to enable AI LLMs to trade using MetaTrader platform