# ADL vs A2A, MCP, and Other Agent Standards

The **Agent Definition Language (ADL)** describes *who an AI agent is* — its identity, capabilities, permissions, security, lifecycle, and compliance posture — in a single auditable, machine-readable document (an "agent passport"). Most other agent standards solve an *adjacent* problem: how agents **communicate** (A2A) or how they **connect to tools and data** (MCP). ADL is complementary to both, and can generate their artifacts.

## Short answer[​](#short-answer "Direct link to Short answer")

* **ADL vs A2A** — A2A defines how agents *talk to each other*; ADL defines *what an agent is and what it's allowed to do*. ADL can [generate A2A Agent Cards](/spec/.md#151-a2a-agent-card-generation). They work together.
* **ADL vs MCP** — MCP defines how a model *connects to tools and context*; ADL defines the agent's identity, permission boundaries, and governance around those tools. ADL can [generate MCP server configurations](/spec/.md#152-mcp-server-configuration). They work together.
* **ADL is not a replacement** for A2A or MCP — it's the **governance and identity layer** above them.

## How the standards divide the problem[​](#how-the-standards-divide-the-problem "Direct link to How the standards divide the problem")

| Layer                     | Question it answers                                         | Standards         |
| ------------------------- | ----------------------------------------------------------- | ----------------- |
| **Identity & governance** | *Who is this agent, what may it do, who authorized it?*     | **ADL**           |
| **Communication**         | *How do agents advertise capabilities and call each other?* | A2A (Agent Cards) |
| **Tools & context**       | *How does the model reach tools and data?*                  | MCP               |

## Feature comparison[​](#feature-comparison "Direct link to Feature comparison")

| Concern                 | A2A Agent Cards | Agent Spec | AGNTCY     | ADL                    |
| ----------------------- | --------------- | ---------- | ---------- | ---------------------- |
| Agent identity          | Partial         | —          | DIDs + VCs | DIDs + attestation     |
| Permissions model       | Partial         | —          | Partial    | Deny-by-default        |
| Governance & compliance | —               | —          | Partial    | NIST, SOC 2, EU AI Act |
| Lifecycle management    | Partial         | —          | Partial    | Status + sunset dates  |
| Agent relationships     | Partial         | Flows      | Partial    | Portfolio profile      |

A2A Agent Cards (Google / Linux Foundation) · Agent Spec (Oracle) · AGNTCY (Cisco / Outshift)

## Detailed comparisons[​](#detailed-comparisons "Direct link to Detailed comparisons")

* [**ADL vs A2A**](/comparisons/adl-vs-a2a.md) — agent identity and governance vs agent-to-agent communication.
* [**ADL vs MCP**](/comparisons/adl-vs-mcp.md) — agent identity and governance vs the model-to-tool protocol.

## Related[​](#related "Direct link to Related")

* [ADL specification](/spec/.md) — the full normative document.
* [Interoperability](/spec/.md#15-interoperability) — how ADL generates A2A Agent Cards, MCP configurations, and integrates with OpenAPI.
* [Glossary](/glossary) · [FAQ](/faq)