AI agents call pruva_list_feature_relations to retrieve information from Pruva without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries feature relation data (dependencies, blocks, relates-to relationships) for a product. It performs a read-only operation that returns information in markdown format. No data is created, modified, deleted, or executed. The blast radius of misuse is minimal—an agent could retrieve relational metadata but cannot alter product state or trigger external operations.
From the tool's definition Tool name is "pruva_list_feature_relations" and description states "List all feature relations... Returns a markdown list." The verb "list" and "returns" indicate retrieval of existing data with no modification or side effects.
Attacks that exploit this kind of access
List all feature relations (dependencies, blocks, relates-to) for a product. Returns a markdown list. It is categorised as a Read tool in the Pruva MCP Server, which means it retrieves data without modifying state.
Register the Pruva MCP server in PolicyLayer and add a rule for pruva_list_feature_relations: 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 Pruva. Nothing to install.
pruva_list_feature_relations 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 pruva_list_feature_relations 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 pruva_list_feature_relations. 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.
pruva_list_feature_relations is provided by the Pruva MCP server (pruva-ai/pruva-mcp). 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 →