ADR-164 Phase 3 — Compute the domain-affinity routing decision for a business pod per ADR-164 §3.4 and return {backend, reason}. The three backends are local-stdio (preferLocalExecution=true), cloud-managed (preferLocalExecution=false AND budgetUsdMonthly >= 50), and remote-peer (everything else ...
AI agents invoke business_pod_route_backend to trigger actions in Ruflo. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool computes and returns a routing decision that determines which backend (local, cloud, or remote peer) a business pod is dispatched to. While it surfaces as an auditable decision, it triggers an external routing operation with real infrastructure consequences — executing a policy that drives downstream pod execution paths.
From the tool's definition Compute the domain-affinity routing decision for a business pod... return {backend, reason}. The three backends are local-stdio, cloud-managed, and remote-peer... route through a federation peer node.
Risk signalsBulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
ADR-164 Phase 3 — Compute the domain-affinity routing decision for a business pod per ADR-164 §3.4 and return {backend, reason}. The three backends are local-stdio (preferLocalExecution=true), cloud-managed (preferLocalExecution=false AND budgetUsdMonthly >= 50), and remote-peer (everything else — small-budget non-local pods route through a federation peer node). Use when a /loop driver, @metaharness/router policy hook, or operator CLI needs the structural routing pick BEFORE the cost-optimal KRR step — surfacing this as an MCP tool keeps the rule auditable from the pod template alone and lets non-TS callers reach it. Re-implementing the rule in the caller is wrong because it forks the §3.4 source-of-truth and skips the {success,valid,error,path} envelope shape callers already rely on from business_pod_validate. Pair with business_pod_validate when pre-flighting a template, since this tool also runs full schema validation and degrades to the same error shape on malformed input. Threshold lives in CLOUD_BUDGET_THRESHOLD_USD in domain-affinity-policy.ts — keep that constant and this description aligned. It is categorised as a Execute tool in the Ruflo MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Ruflo MCP server in PolicyLayer and add a rule for business_pod_route_backend: 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_route_backend is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the business_pod_route_backend 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_route_backend. 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_route_backend 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_route_backend 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 →