A small agency (1-15 person team) building agentic features on paid client work in 2026 should pick its agent protocol per project by reading the client's existing stack (Anthropic-aligned client → MCP; Google-aligned client → A2A; sovereignty- or self-hosted-aligned client → Llama Stack), default to MCP for tool-heavy work and A2A for agent-collaboration work when the client has no existing stack, and keep its tool inventory portable by building every tool as a plain HTTP service first and wrapping it to the chosen protocol second. The plain-HTTP-first discipline costs roughly 20-30% extra on the first tool of a project and produces 60% wrapper-effort reduction on the second client requesting the same functionality on a different protocol. Tracking wrapper hours separately from service hours in the agency's time log is the simplest instrument for quoting the re-platform cost accurately when a client asks.

Claim is scoped to the protocol-picking and portability discipline for a small agency building (not just consuming) agentic features. Quantitative figures (20-30% first-tool cost, 60% re-implementation reduction) are derived from informal reports across 2025-2026 small-agency engagements and would benefit from a published benchmark — flagged in trigger condition 3. 45-day review cadence calibrated to typical SaaS/consulting client review cycles. Trigger conditions: (1) MCP, A2A, and Llama Stack publish a converged or interoperable spec — would move toward Partial because the protocol-picking decision becomes less consequential; (2) one of the major proprietary platforms (Microsoft, Salesforce, SAP, ServiceNow) adopts MCP or A2A as a first-class default — would shift the picking logic materially for clients on those platforms; (3) a published 2026 SMB-services-agency benchmark on protocol-switching costs and HTTP-first portability — would empirically anchor the rule with real numbers and either confirm or revise the cost figures cited; (4) emergence of a multi-protocol wrapper-generator toolkit reducing per-protocol wrapper cost materially — would lower the discipline's cost-of-adoption and broaden the rule's applicability.