Get available runtimes and exams for Proctor testing. Returns the list of available runtime environments (Docker images) and exam types. Returns: - runtimes: Array of runtime configurations with id, name, and Docker image - exams: Array of exam types with id, name, and description Use cases: - Di...
AI agents call get_proctor_metadata to retrieve information from Proctor without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves metadata about available testing resources (runtimes and exams) without modifying, executing, or deleting anything. It is a read-only query operation. The low severity reflects that discovering available options poses minimal security risk, though in context of a testing/proctoring system, information disclosure could have some value to an attacker (hence not lowest confidence).
From the tool's definition Tool description explicitly states it 'Get available runtimes and exams' and 'Returns the list of available runtime environments' and 'exam types' — purely informational retrieval with no side effects.
Attacks that exploit this kind of access
Get available runtimes and exams for Proctor testing. Returns the list of available runtime environments (Docker images) and exam types. Returns: - runtimes: Array of runtime configurations with id, name, and Docker image - exams: Array of exam types with id, name, and description Use cases: - Discover available runtime environments - Find the correct exam ID for a specific test type - Check which runtime versions are available. It is categorised as a Read tool in the Proctor MCP Server, which means it retrieves data without modifying state.
Register the Proctor MCP server in PolicyLayer and add a rule for get_proctor_metadata: 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 Proctor. Nothing to install.
get_proctor_metadata 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_proctor_metadata 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_proctor_metadata. 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_proctor_metadata is provided by the Proctor MCP server (proctor-mcp-server). 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 →