AI agents call score_workflow_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 appears to compute and return a risk score based on workflow inputs. Scoring/analysis functions are fundamentally read/query operations with no direct side effects. However, the server context is financial cybersecurity and the tool analyzes 'vendor/payment change signals', meaning misuse could produce misleading risk assessments that influence financial decisions downstream.
From the tool's definition 'Score end-to-end workflow risk from sequence anomalies, role sensitivity, value, and vendor/payment change signals' — the tool scores/evaluates risk by reading and analyzing workflow data
Attacks that exploit this kind of access
Score end-to-end workflow risk from sequence anomalies, role sensitivity, value, and vendor/payment change signals. 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_workflow_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_workflow_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_workflow_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_workflow_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_workflow_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 →