AI agents call get_request to retrieve information from Qonto MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a Read operation—it retrieves data from the Qonto API without side effects. Severity is medium (not low) because the Qonto server handles sensitive financial data including transaction history, balances, and business operations; unauthorized read access to financial requests could expose confidential business information, though it does not directly move money or delete data.
From the tool's definition Tool name 'get_request' and description 'Get a specific request from Qonto API' indicate data retrieval with no modification.
Documented attack patterns abuse exactly the kind of access get_request gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Qonto MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for get_request:
{
"version": "1",
"default": "deny",
"tools": {
"get_request": {}
}
}get_request is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Get a specific request from Qonto API. It is categorised as a Read tool in the Qonto MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Qonto MCP Server MCP server in PolicyLayer and add a rule for get_request: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Qonto MCP Server. Nothing to install.
get_request is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_request rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for get_request. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
get_request is provided by the Qonto MCP Server MCP server (qonto/qonto-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 21 Qonto MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
21 Qonto MCP Server tools catalogued and risk-classified — across an index of 42,500+ MCP servers.