Get an improved version of your prompt with explanations
AI agents call prompt_score_improve to retrieve information from Scan Your Ai Toolkit without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool takes a prompt as input and returns an improved version with explanations. This is essentially a read/query operation that generates and returns data without modifying external state, executing code, or causing side effects. The output is informational (an improved prompt text plus explanations).
From the tool's definition 'Get an improved version of your prompt with explanations' — retrieves a transformed/improved prompt and explanations
Attacks that exploit this kind of access
Get an improved version of your prompt with explanations. It is categorised as a Read tool in the Scan Your Ai Toolkit MCP Server, which means it retrieves data without modifying state.
Register the Scan Your Ai Toolkit MCP server in PolicyLayer and add a rule for prompt_score_improve: 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 Scan Your Ai Toolkit. Nothing to install.
prompt_score_improve 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 prompt_score_improve 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 prompt_score_improve. 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.
prompt_score_improve is provided by the Scan Your Ai Toolkit MCP server (sakthivelchan89/scan_your_ai_toolkit). 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 →