Get a specific mandate by ID
AI agents call get_mandate to retrieve information from GoCardless MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves mandate data by ID, which is a read-only operation with no side effects. However, severity is elevated to 'medium' rather than 'low' because mandates are sensitive financial instruments that authorize recurring payments; unauthorized access to mandate details could expose authorization data, payment terms, and customer financial commitments, even though the tool itself performs no write or…
From the tool's definition Tool name 'get_mandate' and description 'Get a specific mandate by ID' indicate retrieval of a specific mandate record without modification.
Attacks that exploit this kind of access
Get a specific mandate by ID. It is categorised as a Read tool in the GoCardless MCP Server MCP Server, which means it retrieves data without modifying state.
Register the GoCardless MCP Server MCP server in PolicyLayer and add a rule for get_mandate: 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 GoCardless MCP Server. Nothing to install.
get_mandate 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_mandate 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_mandate. 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_mandate is provided by the GoCardless MCP Server MCP server (jmceleney/gocardless-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →