Get the currently active role
AI agents call roles_current to retrieve information from Claude Role Library without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries the state of the system to return which role is currently active. It performs no writes, deletions, code execution, or financial operations. The worst-case misuse would be information disclosure about which persona is loaded, which is minimal in severity given the local-first architecture and the benign nature of role metadata.
From the tool's definition Tool name 'roles_current' and description 'Get the currently active role' indicate a retrieval operation with no modifications or side effects. The verb 'Get' is explicitly read-only.
Attacks that exploit this kind of access
Get the currently active role. It is categorised as a Read tool in the Claude Role Library MCP Server, which means it retrieves data without modifying state.
Register the Claude Role Library MCP server in PolicyLayer and add a rule for roles_current: 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 Claude Role Library. Nothing to install.
roles_current 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 roles_current 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 roles_current. 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.
roles_current is provided by the Claude Role Library MCP server (tony427/claude-role-library). 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 →