Agent Registry is a centralized, unified catalog that lets you store, discover, and govern Model Context Protocol (MCP) servers, tools, and AI agents within Google Cloud. Agent Registry corresponds to the governance pillar and inventory of your agents, servers, and endpoints in Gemini Enterprise Agent Platform.
As you deploy, implement, and expand AI workloads, Agent Registry provides the core infrastructure for your environment, bringing together autonomous agents with the consistent data contexts and tools that MCP servers offer. By consolidating these services, Agent Registry resolves common challenges in complex AI deployments, such as fragmented tool access, isolated data, and redundant services.
Why use Agent Registry?
Agent Registry is structured around three primary goals to help you manage your agents and MCP servers:
- Accelerate development: Discover and reuse existing agent skills and MCP tools across your organization. You can query the registry to identify and use available functionalities, removing the need to create custom integrations for each new process.
- Simplify integration: Use standardized MCP or Agent2Agent (A2A) protocols to locate and connect to functional endpoints, helping reduce infrastructure management overhead.
- Support governance: Enforce security and implement boundaries across your agentic fleet. Define permissions and establish a unified identity registry to control which agents can access your data.
Data model
A service in Agent Registry represents an agent, an MCP server, or an endpoint that you add manually to your registry.
The Agent Registry API separates read and write operations. You use the writable
Service resource to create, update, and delete entries, but you query the
read-only Agent, McpServer, or Endpoint resources to get, list, and search
for them.
You can discover and manage agents deployed within a Google Cloud project by enabling the Agent Registry API. To get started, see Set up Agent Registry.
Discover services
Agent Registry categorizes services into three main types that you can discover within your environment:
- Agents: Autonomous actors that possess specific skills. Skills represent an agent's high-level capabilities and are a primary mechanism for discovery.
- MCP servers: Providers of standardized data resources and tools. Tools are deterministic functions exposed by an MCP server that agents can invoke to perform specific actions.
- Endpoints: Target URLs, typically REST APIs, accessed by an agent. By abstracting these destinations into manageable resources, Agent Registry lets you centrally govern which external services your agents can access.
Based on the data model, you query the read-only Agent,
McpServer, or Endpoint resources to get, list, and search for services added
manually.
For more information about these and other concepts that Agent Registry uses, see Key concepts.
Register services
Agent Registry maintains your catalog of agents and MCP servers through two registration mechanisms.
Agent Registry separates read and write operations. Based on the
data model, you use the Service resource to create, update, and
delete entries manually.
| Registration mechanism | Description | Agent Registry service | Supported Google Cloud products |
|---|---|---|---|
| Automatic registration | You can configure and use Agent Registry to automatically discover and ingest specific resources deployed on supported Google Cloud runtimes. For agents implementing the open Agent2Agent (A2A) protocol, the registry also automatically extracts their skills and capabilities from their Agent Card. | Agents |
|
| MCP servers | Official Google and Google Cloud remote MCP servers | ||
| Manual registration |
For external resources, custom workloads on unsupported runtimes, or
standard REST agents that don't implement the A2A protocol, you must
manually register them by creating a Service resource in
the registry.
|
Agents | Remote agents |
| MCP servers | Custom workloads or external MCP servers |