upload_file_from_url
AI agents use upload_file_from_url to create or update resources in ERPNext MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your ERPNext MCP Server environment.
This tool creates or stores files in the ERPNext system from external URLs. While reversible (files can be deleted via delete_document), it modifies system state and could be exploited to inject malicious files, overwrite existing data, or consume storage. The high severity reflects the risk in an ERP context where file integrity matters. Confidence is reduced slightly due to the empty description.
From the tool's definition Tool name 'upload_file_from_url' and server context (ERPNext document management) indicate file creation/storage.
Attacks that exploit this kind of access
upload_file_from_url. It is categorised as a Write tool in the ERPNext MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the ERPNext MCP Server MCP server in PolicyLayer and add a rule for upload_file_from_url: 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.
upload_file_from_url 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 upload_file_from_url 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 upload_file_from_url. 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.
upload_file_from_url 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 →