Use this tool to get the direct download URL for a file stored in Canvas. This tool returns a URL string that can be used to access or download the file. Use this when you need direct access to file content rather than just the Canvas page URL.
AI agents call get_file_url to retrieve information from Canvas MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves metadata (a download URL) from Canvas LMS without creating, modifying, or destroying data. It enables read-only access to file resources. No side effects or irreversible changes occur. The blast radius of misuse is minimal—an agent could access files they might not have authorization for, but this is an information disclosure risk rather than destructive or executable risk.
From the tool's definition Tool name 'get_file_url' and description explicitly states it 'returns a URL string' for file access/download. The action is to retrieve/query file location data with no modification, deletion, or execution of code.
Attacks that exploit this kind of access
Use this tool to get the direct download URL for a file stored in Canvas. This tool returns a URL string that can be used to access or download the file. Use this when you need direct access to file content rather than just the Canvas page URL. It is categorised as a Read tool in the Canvas MCP MCP Server, which means it retrieves data without modifying state.
Register the Canvas MCP server in PolicyLayer and add a rule for get_file_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 Canvas MCP. Nothing to install.
get_file_url 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 get_file_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 get_file_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.
get_file_url is provided by the Canvas MCP server (noahjohannessen/canvas-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 →