MCP & AI TOOLING / SYSTEM CONCEPT BRIEF

MCP vs A2A

MCP and A2A solve different connection problems.

AdvancedPhase 12 / Topic 13 of 18RequirementsTrade-offsFailure modes
01

Overview

MCP and A2A solve different connection problems. MCP connects an agent to tools and data, which is a vertical link from an AI app down to capabilities. A2A (Agent-to-Agent) connects agents to other agents, which is a horizontal link between independent, possibly opaque, agents owned by different teams or vendors. They are complementary. An agent may use MCP to reach its tools and A2A to delegate work to a partner agent.

A tool called over MCP is usually a function with a defined input and a quick result. An agent reached over A2A is an autonomous peer. You send it a task, it may take minutes, ask for more input, stream progress, and return artifacts. A2A agents advertise what they can do through an agent card, and the caller does not see their internal tools, prompts, or memory.

Tools vs colleagues

MCP is how a worker picks up tools, such as a calculator, a database terminal, or a stapler. A2A is how a worker hands a job to a colleague in another department, who has their own tools and judgment and reports back when done.

02

When to use it

  • Designing systems where agents from different teams or vendors must cooperate.
  • Deciding whether a capability should be a tool or a separate agent.
  • Explaining the AI integration protocol landscape.
03

Where it shows up in interviews

Tool or agent?

Recognize it when: a capability needs its own reasoning and long-running work.

  • Design a multi-agent system
  • Design Multi-Agent Platform
04

Where it is used in real software

Enterprise workflows

A travel-booking agent delegates expense approval to the finance team's agent over A2A while using MCP for calendar and booking tools.

Vendor ecosystems

SaaS vendors expose their own agents so customers' agents can delegate tasks without seeing vendor internals.

05

Key terms

A2A
An open protocol for agents to discover each other, exchange tasks, and stream results.
Agent card
A published description of an agent's skills, endpoint, and authentication.
Task
A unit of work sent to an agent, with states such as working, input-required, and completed.
Artifact
An output produced by a task, such as a document or data.
Opaque agent
An agent whose internal reasoning and tools are hidden from callers.
06

How it works, step by step

  1. 1
    Discover

    The client agent reads the remote agent's card to learn skills and auth requirements.

  2. 2
    Send a task

    The client submits a task message describing what it needs.

  3. 3
    Remote agent works

    The remote agent uses its own tools (often via MCP) and may request more input.

  4. 4
    Stream updates

    Progress and partial results stream back over the connection.

  5. 5
    Return artifacts

    The completed task returns outputs the client agent can use.

Vertical and horizontal links
Step 1 / 4
Travel agent
MCP tools
A2A
Finance agent
Finance tools

STEP 1The travel agent books flights through MCP tools for airline search and calendar.

07

Comparison

Two protocols, different jobs.

Step 1 / 5
AspectMCPA2A
ConnectsAgent to tools and dataAgent to agent
CalleeFunction-like toolAutonomous agent
DurationUsually quickCan be long-running
VisibilityTool schema is visibleInternals are opaque
Discoverytools/list from a serverAgent card

NOWAspect: Connects | MCP: Agent to tools and data | A2A: Agent to agent

Use MCP for capabilities you control; use A2A to collaborate with other agents.

08

Implementation

{  "name": "Finance Approvals Agent",  "description": "Checks travel requests against budget and policy.",  "url": "https://agents.example.com/finance",  "version": "1.0.0",  "capabilities": { "streaming": true },  "skills": [    { "id": "approve-travel", "name": "Approve travel", "description": "Approve or reject a trip by cost and policy." }  ],  "securitySchemes": { "oauth": { "type": "oauth2" } }}
09

Complexity and performance

MCP callmilliseconds to seconds

Function-like.

A2A taskseconds to hours

May pause for input or human approval.

10

Trade-offs

Tool vs agent boundary

Making everything an agent adds latency and unpredictability. Use a tool when the job is a well-defined function; use an agent when it needs its own reasoning or ownership.

Opacity vs debuggability

Opaque agents protect vendor internals but make end-to-end tracing harder. Agree on task IDs and trace propagation.

11

Variants and related techniques

Framework-specific handoffs

Inside one codebase, frameworks offer direct handoffs without a network protocol.

12

Common mistakes

  • Using A2A for simple function calls.

    Fix: Expose simple capabilities as MCP tools or plain APIs.

  • Trusting remote agents implicitly.

    Fix: Authenticate agents, authorize tasks, and validate returned artifacts.

13

Interview questions

How do MCP and A2A relate?

They are complementary. MCP connects an agent to its tools and data; A2A lets independent agents discover each other and exchange long-running tasks. A remote agent often uses MCP internally.

When would you make a capability a separate agent instead of a tool?

When it needs its own reasoning, owns a domain with its own policies, runs long or needs human input, or is operated by another team or vendor that wants to hide internals.

14

Practice problems

ProblemDifficultyWhat it trains
Write an agent card for a scheduling agentEasyDiscovery.
Design a cross-team agent system using MCP and A2AHardBoundaries, auth, and tracing.