Upload an attachment to a record
AI agents use attachment_upload to create or update resources in ServiceNow MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your ServiceNow MCP Server environment.
Uploading attachments creates new data within ServiceNow records and is reversible (files can be deleted). This is a Write operation rather than Read (no data retrieval), Execute (no arbitrary command execution), Destructive (not irreversible), or Financial (no monetary impact).
From the tool's definition Tool name 'attachment_upload' and description 'Upload an attachment to a record' indicate file creation/modification to an existing ServiceNow record.
Attacks that exploit this kind of access
Upload an attachment to a record. It is categorised as a Write tool in the ServiceNow MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the ServiceNow MCP Server MCP server in PolicyLayer and add a rule for attachment_upload: 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 ServiceNow MCP Server. Nothing to install.
attachment_upload 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 attachment_upload 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 attachment_upload. 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.
attachment_upload is provided by the ServiceNow MCP Server MCP server (schwarztim/servicenow-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 →