Build or update the index for a source. This fetches all prompts metadata (name, description, tags) to enable searching. May take 1-2 minutes for large sources.
AI agents invoke sources_index to trigger actions in Claude Role Library. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
The tool performs an active indexing operation that fetches external data and writes/updates a local index. This goes beyond a pure read — it modifies the local index state. The fetch from external sources and index construction represent an Execute-level operation, as it triggers network requests and modifies local storage state.
From the tool's definition 'Build or update the index for a source. This fetches all prompts metadata' — triggers an external fetch operation and builds/updates an index, which is an active operation with side effects beyond simple data retrieval.
Attacks that exploit this kind of access
Build or update the index for a source. This fetches all prompts metadata (name, description, tags) to enable searching. May take 1-2 minutes for large sources. It is categorised as a Execute tool in the Claude Role Library MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Claude Role Library MCP server in PolicyLayer and add a rule for sources_index: 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_index is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the sources_index 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_index. 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_index 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 →