find_items
AI agents call find_items to retrieve information from ERPNext MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool name and pattern of sibling read operations (get_item_details, get_document, get_count) indicate this is a search/retrieval function that queries ERPNext inventory data without modifying state. No evidence of write, delete, execute, or financial operations. Classified as Read with low severity due to the informational nature of item lookups.
From the tool's definition Tool name 'find_items' combined with server context showing it retrieves item information, consistent with sibling tool 'get_item_details' which performs read operations. Description is empty, reducing confidence slightly.
Attacks that exploit this kind of access
find_items. It is categorised as a Read tool in the ERPNext MCP Server MCP Server, which means it retrieves data without modifying state.
Register the ERPNext MCP Server MCP server in PolicyLayer and add a rule for find_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 ERPNext MCP Server. Nothing to install.
find_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 find_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 find_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.
find_items is provided by the ERPNext MCP Server MCP server (yazelin/erpnext-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 →