Find mismatches between invoices, purchase orders, and shipping orders.
AI agents call find_document_gaps to retrieve information from Caseware Kb without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool queries and analyzes existing procurement documents to identify mismatches—a pure read operation. It retrieves and compares data but does not create, modify, delete, or execute external operations. Gap analysis is inherently an inspection/reporting function with no side effects on the data itself.
From the tool's definition Tool description: 'Find mismatches between invoices, purchase orders, and shipping orders.' This performs analysis and comparison of existing procurement documents to identify gaps/discrepancies.
Attacks that exploit this kind of access
Find mismatches between invoices, purchase orders, and shipping orders. It is categorised as a Read tool in the Caseware Kb MCP Server, which means it retrieves data without modifying state.
Register the Caseware Kb MCP server in PolicyLayer and add a rule for find_document_gaps: 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 Caseware Kb. Nothing to install.
find_document_gaps 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 find_document_gaps 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 find_document_gaps. 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.
find_document_gaps is provided by the Caseware Kb MCP server (leonardorhojas/caseware-procurement-kb). 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 →