AI agents call list_communication_ways 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 and returns communication data associated with contacts. It performs a read-only operation that retrieves existing information without creating, modifying, deleting, or executing any business logic. The blast radius of misuse is minimal—an attacker could enumerate contact communication details but cannot alter data or trigger financial/operational consequences.
From the tool's definition Tool name 'list_communication_ways' and description 'List communication ways (email, phone, etc.) for contacts' indicate a retrieval operation with no modification or side effects.
Attacks that exploit this kind of access
List communication ways (email, phone, etc.) for contacts. 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_communication_ways: 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_communication_ways 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_communication_ways 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_communication_ways. 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_communication_ways 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 →