Qonto-MCP-Server
MCP Server for the Qonto API.
Documentation
Qonto-MCP-Server
MCP Server for the Qonto API.
Supported API Methods
This MCP server supports all endpoints of Qonto's Business API that are accessible via API key authentication. For a comprehensive list of these endpoints, please refer to the official Qonto documentation:
๐ Endpoints accessible with an API key
Installation
Using uv (recommended)
When using `uv` no specific installation is needed. We will
use `uvx` to directly run _qonto-mcp-server_.
Using PIP
Alternatively you can install `qonto-mcp-server` via pip:
pip install qonto-mcp-serverConfiguration
Usage with Claude Desktop
Add this to your `claude_desktop_config.json`:
- Note: For details on how to obtain `API_LOGIN` and `API_SECRET_KEY` values, see the Qonto API key docs.
Using uvx
"mcpServers": {
"qonto-mcp-server": {
"command": "uvx",
"args": ["qonto-mcp-server", "--api-key", "API_LOGIN:API_SECRET_KEY"]
}
}Using pip installation
"mcpServers": {
"qonto-mcp-server": {
"command": "python",
"args": ["-m", "qonto-mcp-server", "--api-key", "API_LOGIN:API_SECRET_KEY"]
}
}Frequently asked questions
What is Qonto-MCP-Server?
Qonto-MCP-Server is MCP Server for the Qonto API.
How do I install Qonto-MCP-Server?
Open the GitHub repository and follow its README. Most MCP servers are added to your client's MCP config, then called by your agent.
Is Qonto-MCP-Server open source?
Yes โ it is hosted on GitHub at https://github.com/j-about/Qonto-MCP-Server and has 3 stars.
Related MCP tools
Cognee is the open-source AI memory platform for agents. Give your AI agents persistent long-term memory across sessions with a self-hosted knowledge graph engine.
Automate browser based workflows with AI
Hindsight: Agent Memory That Learns
A privacy-first app that strips AI watermarks from content you own.
Agent framework and applications built upon Qwen>=3.0, featuring Function Calling, MCP, Code Interpreter, RAG, Chrome extension, etc.
The power of Claude Code / GeminiCLI / CodexCLI + [Gemini / OpenAI / OpenRouter / Azure / Grok / Ollama / Custom Model / All Of The Above] working as one.
Run your own MCP server? See who uses it and what to fix.
Measure it with TrackMCP