MCP

Model Context Protocol

Anthropic

Standardizes how AI connects to external tools and data sources. Like an "AI's USB-C port" — one protocol to access databases, APIs, file systems, and more.

Agent ↔ Tool / Data
ToolIntegrationContext

A2A

Agent-to-Agent Protocol

Google

Enables interoperability between AI agents across vendors and frameworks. Agents discover, delegate, and collaborate — a "diplomatic protocol" for AI.

Agent ↔ Agent
InteroperabilityCollaboration

MCP connects agents with tools. A2A connects agents with agents.

Start here

Top Picks

High-signal entries to start exploring the A2A and MCP ecosystem.

New arrivals

Latest Entries

Recently added resources for people who want to track what is new.

Ecosystem Directory

Browse through curated categories of A2A and MCP ecosystem resources.

MCP Servers

MCP-compatible servers providing tools, data, and API integrations for AI models.

A2A Agents

Agents using the A2A protocol for cross-vendor collaboration and task delegation.

AI Agents

Autonomous AI agents for coding, browsing, research, and workflow automation.

Frameworks & SDKs

SDKs, libraries, and frameworks for building agents and protocol integrations.

Tools & Extensions

Developer tools, extensions, and ecosystem utilities.

FAQ

Common questions from builders exploring A2A and MCP.

What is MCP?

MCP is a protocol for connecting AI models and agents to tools, files, databases, APIs, and other context sources through a common interface.

What is A2A?

A2A focuses on agent-to-agent interoperability, helping agents discover capabilities, delegate work, and coordinate across vendors or frameworks.

How do I choose an MCP server?

Start with the workflow you need, then check official status, recent activity, client compatibility, security notes, and installation requirements.

Can I submit a project?

Yes. Submit servers, clients, agents, frameworks, guides, and ecosystem resources for review so they can be listed in the directory.