ADR-164 Phase 2 — Validate a business-pod template JSON against the schema in ADR-164 §3.3 (name, agents[], allowedMcpTools, bench, piiPolicy, budgets, cronSchedule, auditReadView, reservationExpiryMs bounded by ADR-164.1 §3.2). Use when a /loop driver or CI workflow needs to pre-flight a pod tem...
AI agents call business_pod_validate to retrieve information from Ruflo without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a validation/query tool that reads and validates a template structure without side effects. It checks conformance to a schema and returns validation results. This is a read operation with no modifications to state, no execution of arbitrary code, and no destructive capabilities. Severity is low because misuse would only result in incorrect validation feedback, not system harm.
From the tool's definition Tool validates a business-pod template JSON against a schema (ADR-164 §3.3) and surfaces validation results.
Attacks that exploit this kind of access
ADR-164 Phase 2 — Validate a business-pod template JSON against the schema in ADR-164 §3.3 (name, agents[], allowedMcpTools, bench, piiPolicy, budgets, cronSchedule, auditReadView, reservationExpiryMs bounded by ADR-164.1 §3.2). Use when a /loop driver or CI workflow needs to pre-flight a pod template before pod-tick.mjs reaches it — surfacing validation as JSON keeps the optional-dep degraded path clean. Hand-parsing the JSON in the caller is wrong because it skips the JSON-pointer error path and the reservationExpiryMs [5000, 300000] ms bound check that ADR-164.1 mandates. Pair with business_pod_validate -> pod-tick.mjs in the sales-pod smoke contract. It is categorised as a Read tool in the Ruflo MCP Server, which means it retrieves data without modifying state.
Register the Ruflo MCP server in PolicyLayer and add a rule for business_pod_validate: 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 Ruflo. Nothing to install.
business_pod_validate 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 business_pod_validate 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 business_pod_validate. 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.
business_pod_validate is provided by the Ruflo MCP server (ruvnet/ruflo). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
business_pod_validate is one line of Ruflo's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →