browser_upload
Set local files on a file input of the browser tools' tab by its snapshot ref (in Moodle's file picker, the "Upload a file" input), as if the person had chosen them. Absolute paths. A fallback: use it only when no Moodle tool covers the task, and say which task, so a tool can be made for it.
This record as markdown: /tools/falkenslab-moodle-mcp/browser-upload.md
What browser_upload does on Moodle
AI agents use browser_upload to create or update resources in Moodle, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Moodle environment.
| Parameter | Type | Required | Description |
|---|---|---|---|
ref | string | Yes | The element's ref from the latest browser_snapshot, like e12 |
paths | array | Yes | Absolute paths of local files |
Parameters from the server's own tool schema.
Why browser_upload is rated Medium
An AI agent can call browser_upload faster than any human can review: one bad instruction and it creates or modifies resources in Moodle by the hundred, each call as confident as the last.
Attacks that exploit this kind of access
The rule that runs browser_upload safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Moodle, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For browser_upload, this is the rule to start with:
browser_upload 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 Moodle, apply this rule, and every browser_upload call is checked against it from then on.
Questions about browser_upload
Set local files on a file input of the browser tools' tab by its snapshot ref (in Moodle's file picker, the "Upload a file" input), as if the person had chosen them. Absolute paths. A fallback: use it only when no Moodle tool covers the task, and say which task, so a tool can be made for it. It is categorised as a Write tool in the Moodle MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
browser_upload accepts 2 parameters: ref, paths. Required: ref, paths. The full parameter table on this page comes from the server's own tool schema.
Register the Moodle MCP server in PolicyLayer and add a rule for browser_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 Moodle. Nothing to install.
browser_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 browser_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 browser_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.
browser_upload is provided by the Moodle MCP server (@falkenslab/moodle-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Moodle, and thousands of servers like it.
This server
Across the catalogue