upload_asset
Upload one or more files (images, fonts, CSS, video, etc.) as assets and receive stable URLs. Use these URLs in your HTML with <img src> or @font-face. Assets are cached on displays. Pass files as base64-encoded data. Requires authentication with at least content_only scope.
This record as markdown: /tools/de-agentview-agentview-mcp/upload-asset.md
What upload_asset does on agentView
AI agents use upload_asset to create or update resources in agentView, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your agentView environment.
| Parameter | Type | Required | Description |
|---|---|---|---|
files | array | Yes | Array of file objects, each with 'name' (filename with extension) and 'data' (base64-encoded content). |
group_id | string | — | Optional group ID to associate the assets with. |
access_token | string | — | Optional bearer token; prefer session_request_id. |
descriptions | object | Yes | JSON object mapping each filename to a human-readable description. |
Parameters from the server's own tool schema.
Why upload_asset is rated Medium
upload_asset creates and stores new files/assets on the system, which is a reversible write operation. While it doesn't execute code or delete data, it does create persistent digital artifacts that consume storage and can be referenced in content. The requirement for 'content_only scope' authentication suggests access control is in place.
From the tool's definition Tool description states 'Upload one or more files (images, fonts, CSS, video, etc.) as assets and receive stable URLs.' This is a create/write operation that stores new data (files) on a server and returns URLs for reference.
Risk signalsHandles credentials or secrets (access_token)
Attacks that exploit this kind of access
The rule that runs upload_asset safely
PolicyLayer is an MCP gateway: it sits between your AI agents and agentView, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For upload_asset, this is the rule to start with:
upload_asset stays usable, but capped: an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect agentView, apply this rule, and every upload_asset call is checked against it from then on.
Questions about upload_asset
Upload one or more files (images, fonts, CSS, video, etc.) as assets and receive stable URLs. Use these URLs in your HTML with <img src> or @font-face. Assets are cached on displays. Pass files as base64-encoded data. Requires authentication with at least content_only scope. It is categorised as a Write tool in the agentView MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
upload_asset accepts 4 parameters: files, group_id, access_token, descriptions. Required: files, descriptions. The full parameter table on this page comes from the server's own tool schema.
Register the agentView MCP server in PolicyLayer and add a rule for upload_asset: 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 agentView. Nothing to install.
upload_asset 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_asset 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_asset. 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_asset is provided by the agentView MCP server (https://agentview.de/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on agentView, and thousands of servers like it.
This server
Across the catalogue