AI agents call canvas_find_person to retrieve information from Canvas without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a query operation to retrieve student/staff roster information from Canvas LMS. It has no side effects—it only reads and returns existing data (user IDs and roles). While it could inform subsequent actions, the tool itself is purely informational.
From the tool's definition Tool searches and retrieves people enrolled in a course, returning user id and role. Description indicates 'search' and 'get' operations with no modification or deletion capability.
Attacks that exploit this kind of access
Search the people enrolled in a course by name to get their numeric user id and role. It is categorised as a Read tool in the Canvas MCP Server, which means it retrieves data without modifying state.
Register the Canvas MCP server in PolicyLayer and add a rule for canvas_find_person: 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. Nothing to install.
canvas_find_person 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_find_person 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_find_person. 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_find_person is provided by the Canvas MCP server (tylergibbs1/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 →