Get details of a specific role
AI agents call roles_get 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 retrieves information about a stored AI persona role. It queries existing data without modifying, deleting, or executing anything. The operation is non-destructive and informational in nature. Minimal blast radius if misused—an agent retrieving role details cannot cause harm beyond information disclosure of locally-stored persona definitions.
From the tool's definition Tool name 'roles_get' and description 'Get details of a specific role' indicate a retrieval operation with no side effects. The verb 'get' and context of querying role details from a persona library confirms read-only semantics.
Attacks that exploit this kind of access
Get details of a specific 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_get: 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_get 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_get 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_get. 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_get 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 →