AI agents call list_scorecard_submissions 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 and queries existing scorecard data without creating, modifying, deleting, or executing any operations. The ability to filter results does not change its fundamental read-only nature. Blast radius is minimal—an AI could at worst retrieve scorecard information it shouldn't see, a data exposure risk rather than a system-level threat.
From the tool's definition Tool description states 'List scorecards for a specific application' with filtering capability—purely a retrieval operation with no modification, deletion, or execution of external operations.
Attacks that exploit this kind of access
List scorecards for a specific application. Each scorecard may be linked to an interview, assessment, or review — use the type filter to narrow by activity type. 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 list_scorecard_submissions: 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.
list_scorecard_submissions 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 list_scorecard_submissions 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 list_scorecard_submissions. 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.
list_scorecard_submissions 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 →