List all configured prompt sources
AI agents call sources_list 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 and returns existing configuration data (prompt sources) without creating, modifying, deleting, or executing anything. It is a straightforward listing operation with minimal risk. Confidence is high because the verb 'list' clearly indicates read-only behavior, and the description contains no modifiers suggesting write or execute capabilities.
From the tool's definition Tool name 'sources_list' and description 'List all configured prompt sources' indicate a read-only retrieval operation with no side effects.
Attacks that exploit this kind of access
List all configured prompt sources. 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 sources_list: 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.
sources_list 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 sources_list 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 sources_list. 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.
sources_list 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 →