AI agents call search_documents 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.
This tool retrieves and filters existing bookkeeping records based on search criteria. It is a read-only operation that queries local DATEV data without side effects. The blast radius of misuse is minimal—an attacker could access sensitive financial records they shouldn't see, but cannot modify or delete data, nor execute code or move money.
From the tool's definition Tool name 'search_documents' and description 'Searches bookings by text, Belegfeld1 and Belegfeld2' indicate a query/search operation with no modification capability. No deletion, creation, or execution of external operations described.
Attacks that exploit this kind of access
Searches bookings by text, Belegfeld1 and Belegfeld2. 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 search_documents: 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.
search_documents 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 search_documents 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 search_documents. 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.
search_documents 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 →