AI agents use update_check_account 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.
The tool creates or modifies data (a bank account record) in a reversible manner. While it touches financial infrastructure, it does not move money or create financial obligations itself—it updates account metadata/configuration. This is categorized as Write rather than Financial because the action modifies the account record itself rather than executing a payment or transaction.
From the tool's definition Tool name 'update_check_account' and description 'Update an existing bank account in sevdesk' indicate modification of bank account data. This is a reversible write operation that modifies financial records.
Attacks that exploit this kind of access
Update an existing bank account in sevdesk. 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_check_account: 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_check_account 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_check_account 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_check_account. 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_check_account 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 →