canvas_get_grades
AI agents call canvas_get_grades to retrieve information from Canvas LMS MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves grade information from a Canvas LMS instance. It performs a read-only operation with no side effects—it queries and returns existing data without creating, modifying, or deleting records. The blast radius of misuse is limited to unauthorized information disclosure of the user's own grades or potentially classmates' grades if the tool supports filtering.
From the tool's definition Tool name 'canvas_get_grades' indicates retrieval of grade data. The server description states it enables retrieval of 'grades' from student accounts. The tool name uses 'get', a read-only verb.
Attacks that exploit this kind of access
canvas_get_grades. It is categorised as a Read tool in the Canvas LMS MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Canvas LMS MCP Server MCP server in PolicyLayer and add a rule for canvas_get_grades: 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 LMS MCP Server. Nothing to install.
canvas_get_grades 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 canvas_get_grades 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 canvas_get_grades. 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.
canvas_get_grades is provided by the Canvas LMS MCP Server MCP server (sweeden-ttu/canvas-lms-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 →