AI agents use update_communication_way to create or update resources in Sevdesk — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Sevdesk environment.
This tool creates or modifies data reversibly without deleting information or executing code. Communication ways are contact metadata (phone numbers, emails, addresses for correspondence). Updating them has minimal blast radius—the worst case is incorrect contact details being stored temporarily, easily corrected. This is a classic Write operation per the classification scheme.
From the tool's definition Tool name 'update_communication_way' and description 'Update an existing communication way' indicate modification of existing data. The operation is reversible (communication ways can be updated again or reverted).
Attacks that exploit this kind of access
Update an existing communication way. It is categorised as a Write tool in the Sevdesk MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Sevdesk MCP server in PolicyLayer and add a rule for update_communication_way: 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.
update_communication_way is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the update_communication_way 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 update_communication_way. 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.
update_communication_way 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 →