AI agents call get_scorecard_template to retrieve information from Kula Ai without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves structured data (scorecard template configuration) without side effects. It queries existing template information for display or reference purposes, typical of Read category tools. There is no capability to modify, delete, or execute external operations. Low severity due to minimal blast radius—misuse would only expose template metadata already stored in the system.
From the tool's definition The tool description indicates it 'Get[s] full details for a single scorecard template' with no mention of modifying, creating, or deleting data. The verb 'get' and the retrieval-only nature of fetching template details confirm this is a read operation.
Attacks that exploit this kind of access
Get full details for a single scorecard template — questions, feedback/rating descriptions, and segmentation. It is categorised as a Read tool in the Kula Ai MCP Server, which means it retrieves data without modifying state.
Register the Kula Ai MCP server in PolicyLayer and add a rule for get_scorecard_template: 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 Kula Ai. Nothing to install.
get_scorecard_template 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 get_scorecard_template 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 get_scorecard_template. 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.
get_scorecard_template is provided by the Kula Ai MCP server (kula-ai/kula-mcp-server). 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 →