AI agents call get_next_customer_number to retrieve information from Sevdesk without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries sevdesk to retrieve the next sequential customer number, which is a read-only operation with no side effects. The blast radius of misuse is minimal—an AI agent retrieving a customer number presents no financial risk, data loss, or system compromise. Classification as 'Read' is appropriate.
From the tool's definition Tool name 'get_next_customer_number' and description 'Get the next available customer number from sevdesk' indicate a query operation that retrieves data without modifying or deleting anything.
Attacks that exploit this kind of access
Get the next available customer number from sevdesk. It is categorised as a Read tool in the Sevdesk MCP Server, which means it retrieves data without modifying state.
Register the Sevdesk MCP server in PolicyLayer and add a rule for get_next_customer_number: 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 Sevdesk. Nothing to install.
get_next_customer_number 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_next_customer_number 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_next_customer_number. 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_next_customer_number is provided by the Sevdesk MCP server (codestra/sevdesk-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 →