Return all permissions and callable tools for a given role.
AI agents call get_role_permissions to retrieve information from MCPDischarge without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a Read operation: it retrieves RBAC configuration and permissions without side effects. However, severity is elevated to 'high' because exposure of role permissions in a hospital discharge coordination system with PHI boundary enforcement could enable an agent to map the access control matrix, identify privilege escalation opportunities, or circumvent intended authorization barriers.
From the tool's definition Tool name and description indicate it 'Return[s] all permissions and callable tools for a given role' — a query operation that retrieves role-based access control (RBAC) metadata without modifying data.
Attacks that exploit this kind of access
Return all permissions and callable tools for a given role. It is categorised as a Read tool in the MCPDischarge MCP Server, which means it retrieves data without modifying state.
Register the MCPDischarge MCP server in PolicyLayer and add a rule for get_role_permissions: 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 MCPDischarge. Nothing to install.
get_role_permissions 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_role_permissions 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_role_permissions. 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_role_permissions is provided by the MCPDischarge MCP server (prashantsingh1234/mcp_project). 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 →