---
title: "Protocols & Standards"
description: "The protocol landscape for agent-to-service and agent-to-agent communication"
url: "https://agentsurface.dev/docs/protocols"
lastVerified: 2026-09-25
lastModified: 2026-09-25T05:46:01.000Z
---



## Summary [#summary]

Two protocols dominate: MCP (agent-to-tools/data, vertical) and A2A (agent-to-agent, horizontal). Most production systems layer them: agents use MCP to access their tools and A2A to delegate to peers. Commerce protocols (UCP, ACP) that ride on top of these for agent-initiated purchases now have their own section - see [Agentic Commerce](/docs/agentic-commerce). Supporting standards (OpenTelemetry, llms.txt) add observability and API discovery.

```
Orchestrator (uses A2A)
  ├── MCP → tools
  ├── MCP → data
  ├── A2A → Specialist 1
  │    └── MCP → Specialist's tools
  └── A2A → Specialist 2
       └── MCP → Specialist's tools
```

* MCP: remote tools, resources, and prompts - `2026-07-28` is the current revision and is supported by all Tier 1 SDKs; async Tasks are an official extension
* WebMCP: page-scoped browser tools through `document.modelContext`; a W3C Community Group draft, not remote MCP
* A2A v1.0.1: production-grade task delegation across organizational boundaries
* Commerce (UCP, ACP): agent-initiated purchases - see [Agentic Commerce](/docs/agentic-commerce), not covered on this page
* Publish: /.well-known/agent-card.json, /AGENTS.md, /llms.txt
* Transport: stdio (local), Streamable HTTP (remote)

These protocols and complementary standards define how agents discover capabilities, execute work, and integrate across organizational boundaries.

## Quick Start [#quick-start]

**Does your agent need remote tools or data?** → Use [MCP](/docs/protocols/mcp). `2026-07-28` is the current revision, with a stateless core and no sessions, and all Tier 1 SDKs support it. Retain `2025-11-25` compatibility only when a real client still requires it.

**Does a page need to expose tools while an agent visits it?** → Use [WebMCP](/docs/protocols/webmcp). It is a browser proposal built around `document.modelContext`; it does not require or replace the remote MCP wire protocol.

**Multiple agents delegating work?** → Add [A2A](/docs/protocols/a2a) (v1.0.1) for peer-to-peer task delegation.

**Agent initiating purchases?** → See [Agentic Commerce](/docs/agentic-commerce) for UCP and ACP, payment authority, and trust and risk. Note that "ACP" is overloaded with two unrelated protocols; the [Checkout Protocols](/docs/agentic-commerce/checkout-protocols) page disambiguates them.

**Complex multi-step workflows?** → Use [Arazzo](/docs/protocols/comparison#arazzo---here-is-the-workflow-sequence) to choreograph API sequences.

**Need observability?** → Instrument with [OpenTelemetry GenAI semconv](/docs/testing/observability) - widely adopted, but still marked Development.

## The Protocols [#the-protocols]

| Protocol                 | Purpose                                  | Learn More                                               |
| ------------------------ | ---------------------------------------- | -------------------------------------------------------- |
| **MCP 2026-07-28**       | Agent-to-tool / agent-to-data (vertical) | [MCP docs](/docs/protocols/mcp)                          |
| **WebMCP draft**         | Page-scoped browser tools                | [WebMCP docs](/docs/protocols/webmcp)                    |
| **A2A v1.0.1**           | Agent-to-agent delegation (horizontal)   | [A2A docs](/docs/protocols/a2a)                          |
| **UCP / ACP (commerce)** | Agent-initiated commerce                 | [Agentic Commerce](/docs/agentic-commerce)               |
| **Arazzo 1.1.0**         | Multi-step API workflow sequences        | [Comparison page](/docs/protocols/comparison)            |
| **OpenTelemetry GenAI**  | Observability & tracing                  | [Testing: Observability](/docs/testing/observability)    |
| **AGENTS.md**            | Agent context documentation              | [Emerging standards](/docs/protocols/emerging-standards) |
| **llms.txt**             | LLM-friendly API docs                    | [Emerging standards](/docs/protocols/emerging-standards) |

## Architecture Pattern [#architecture-pattern]

Most production systems use MCP + A2A + supporting standards:

```
Orchestrator Agent (uses A2A)
  ├── MCP → Internal tools
  ├── MCP → Data sources
  ├── A2A → Specialist Agent 1
  │    └── MCP → Specialist's tools
  └── A2A → Specialist Agent 2
       └── MCP → Specialist's tools
```

## Discovery Checklist [#discovery-checklist]

Publish these endpoints for agents to find you:

* `/.well-known/agent-card.json` - A2A AgentCard (for multi-agent scenarios)
* `/.well-known/ucp` or `/.well-known/acp.json` - commerce capabilities (if you accept agent-initiated payments) - see [Agentic Commerce](/docs/agentic-commerce)
* `/AGENTS.md` - Agent context & MCP servers (always useful)
* `/llms.txt` or `/llms-full.txt` - LLM-friendly docs
* Structured data as JSON-LD (schema.org markup) for auto-discovery

## Full Comparison & Decision Guide [#full-comparison--decision-guide]

See [Protocol Comparison](/docs/protocols/comparison) for maturity, transport details, auth models, and when to use each.

See [Emerging Standards](/docs/protocols/emerging-standards) for draft specs to monitor.

## Paid resources and structured discovery [#paid-resources-and-structured-discovery]

* [Payments](/docs/agentic-commerce/payments): MPP, x402, mandates, and spending controls for paid resources and agent-initiated purchases.
* [Agent Catalogs and Structured Feeds](/docs/discovery/catalogs-and-feeds): ARD, AI Catalog, and NLWeb feed/query boundaries.