# Agent2Agent Protocol vs Model Context Protocol

The map lists them as complementary: sites and agents commonly implement both. They answer different questions: Agent2Agent Protocol is a step 6 (Coordinate) standard, Model Context Protocol step 5 (Act), so they are not substitutes.

[6 Coordinate](/category/coordinate/) [Agent2Agent Protocol](/protocols/a2a/) · [5 Act](/category/act/) [Model Context Protocol](/protocols/mcp/)

|  | [Agent2Agent Protocol](/protocols/a2a/) A2A | [Model Context Protocol](/protocols/mcp/) MCP |
| --- | --- | --- |
| Lifecycle step | 6 Coordinate: Talk to another agent | 5 Act: Do something for me |
| Answers | How do two independent agents, built on different frameworks, discover each other and delegate a task to completion? | How does an AI application call tools and pull structured context, prompts, and data from an external server? |
| Governed by | Linux Foundation; Technical Steering Committee with AWS, Cisco, Google, IBM Research, Microsoft, Salesforce, SAP, ServiceNow | Agentic AI Foundation (Linux Foundation umbrella); day-to-day spec work in the modelcontextprotocol GitHub org via public SEPs (Specification Enhancement Proposals) and working groups |
| Status (issuer's words) | Stable, v1.0.0 | Active open specification, current dated release 2026-07-28 |
| Phase | stable | living |
| Version | 1.0.1 (2026-05-28) | 2026-07-28 (2026-07-28) |
| Form / transport | endpoint | endpoint |
| Found at | /.well-known/agent-card.json | GET {endpoint}/server-card (SEP-2127 Server Card, Final 2026-10-06; found via an AI Catalog entry) |
| Adoption | claimed — Linux Foundation | claimed — Wikipedia (OpenAI, Google DeepMind adopted MCP by March 2025) and WorkOS ('adopted by OpenAI, Google DeepMind, Microsoft, and thousands of development teams') |
| Evidence | 4 verified, 1 reported | 7 verified, 2 reported |
| Primary use case | Let agents talk to other agents | Expose tools to agents |
| Last verified | 2026-10-19 (current) | 2026-10-19 (current) |
| Specification | [https://a2a-protocol.org/latest/specification/](https://a2a-protocol.org/latest/specification/) | [https://modelcontextprotocol.io/specification/2026-07-28/index](https://modelcontextprotocol.io/specification/2026-07-28/index) |

## When to use which

- Choose Agent2Agent Protocol when your question is “How do two independent agents, built on different frameworks, discover each other and delegate a task to completion?” and you accept its maturity: phase stable, adoption claimed (Linux Foundation).
- Choose Model Context Protocol when your question is “How does an AI application call tools and pull structured context, prompts, and data from an external server?” and you accept its maturity: phase living, adoption claimed (Wikipedia (OpenAI, Google DeepMind adopted MCP by March 2025) and WorkOS ('adopted by OpenAI, Google DeepMind, Microsoft, and thousands of development teams')).

Guidance is derived from the two records (question, phase, adoption, prerequisites, pairings), not from opinion. Each record's page carries its numbered references.

## Read the full articles

- [Agent2Agent Protocol](/protocols/a2a/): How do two independent agents, built on different frameworks, discover each other and delegate a task to completion?
- [Model Context Protocol](/protocols/mcp/): How does an AI application call tools and pull structured context, prompts, and data from an external server?

Ask the MCP server to compare any two: the compare-protocols prompt, or get on both ids. [Connect](/connect/).

[a2a.json](/data/protocols/a2a.json) · [mcp.json](/data/protocols/mcp.json) · [Markdown](/compare/a2a-vs-mcp/index.md)