Architecture health score from domain governance (violations, drift, boundary risks).
AI agents call domain_health to retrieve information from BLUEPRINT MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries architectural metadata and computes/reports health metrics. It has no side effects, does not modify code or configuration, does not execute operations, and does not move money. It is purely informational and advisory in nature, fitting the Read category (retrieves or queries data; no side effects).
From the tool's definition Tool returns a health score and metrics (violations, drift, boundary risks) with no modification capability. Description indicates reporting/assessment only: 'Architecture health score from domain governance'.
Attacks that exploit this kind of access
Architecture health score from domain governance (violations, drift, boundary risks). It is categorised as a Read tool in the BLUEPRINT MCP MCP Server, which means it retrieves data without modifying state.
Register the BLUEPRINT MCP server in PolicyLayer and add a rule for domain_health: 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 BLUEPRINT MCP. Nothing to install.
domain_health 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 domain_health 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 domain_health. 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.
domain_health is provided by the BLUEPRINT MCP server (vedv7/blueprint.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 →