AI agents call list_contacts 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 retrieves/queries contact data with no side effects or modifications. It is a standard read operation that returns existing contact records. No data is created, modified, deleted, or financial actions are triggered. Severity is low because unauthorized read access to contact metadata has limited blast radius compared to write/delete/financial operations on the same server.
From the tool's definition Tool name is 'list_contacts' and description states it 'List contacts (customers, suppliers, partners) from sevdesk'. The verb 'list' indicates data retrieval without modification.
Attacks that exploit this kind of access
List contacts (customers, suppliers, partners) 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 list_contacts: 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.
list_contacts 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 list_contacts 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 list_contacts. 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.
list_contacts 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 →