AI agents call get_open_items to retrieve information from Datev without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
get_open_items retrieves and displays financial data (open items/accounts receivable/payable) from an already-loaded local file without modifying, deleting, or executing external operations. This is a straightforward data retrieval (Read) task with minimal blast radius if misused—an AI agent could only over-query or leak sensitive bookkeeping information, not alter records or move money.
From the tool's definition Tool description states it 'Lists open debtor or creditor items' — a query operation that retrieves data. The server reads DATEV bookkeeping files and provides tools for 'balances, open items, and booking search,' all read-only operations on already-loaded…
Attacks that exploit this kind of access
Lists open debtor or creditor items from the loaded DATEV file. It is categorised as a Read tool in the Datev MCP Server, which means it retrieves data without modifying state.
Register the Datev MCP server in PolicyLayer and add a rule for get_open_items: 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 Datev. Nothing to install.
get_open_items 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_open_items 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_open_items. 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_open_items is provided by the Datev MCP server (ppronobis/datev-mcp-server). 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 →