AI agents call score_human_risk to retrieve information from Scorton without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool performs a risk scoring computation, which is fundamentally a read/query operation — it evaluates and returns a score based on input data. However, given the financial workflow context and that the output could influence downstream security or access decisions, misuse could have medium severity. No evidence of writes, deletions, or financial transactions being triggered directly by this tool.
From the tool's definition 'Score behavioral cybersecurity risk for a human actor in a financial workflow' — the tool computes/reads a risk score, implying a query/analysis operation with no described side effects
Attacks that exploit this kind of access
Score behavioral cybersecurity risk for a human actor in a financial workflow. It is categorised as a Read tool in the Scorton MCP Server, which means it retrieves data without modifying state.
Register the Scorton MCP server in PolicyLayer and add a rule for score_human_risk: 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 Scorton. Nothing to install.
score_human_risk 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 score_human_risk 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 score_human_risk. 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.
score_human_risk is provided by the Scorton MCP server (yojedesign/scorton-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 →