Developer toolsPublic source

A2A Remote Agent MCP Server

Agent-to-Agent protocol management for ADK-Rust Enterprise. Discover remote agents, send tasks, stream results, and manage push notifications — across any framework that implements the A2A protocol.

Open the source Read the official guide ↗

What it gives an agent

A purpose-built capability behind one MCP connection.

The server owns its domain logic and publishes a tool contract an MCP client can discover. ADK-Rust can load that contract into an agent, normalize each schema for the chosen model provider, and keep the connection lifecycle outside the agent’s business logic.

Provides a2a capabilities through a typed MCP contract.

Architecture

How A2A Remote Agent MCP Server fits into an agent system.

The model never needs the implementation details or credentials of the system behind the server. It sees reviewed tool definitions. The MCP client handles discovery and calls, while the server keeps ownership of validation, policy, and communication with its domain system.

ADK-Rust agent

Chooses a capability from the reviewed tool catalog.

→

MCP client

Discovers schemas, sends calls, and receives typed content.

→

A2A Remote Agent MCP Server

Validates the request and owns 11 documented tool contracts.

→

Domain system

Keeps the API, data, credentials, and business rules behind the server.

Connection: stdio · streamable HTTP · SSE · Server framework: ADK MCP SDK + rmcp

A2A Remote Agent MCP Server architecture diagram from its official repository

Tool catalog

What can an agent ask A2A Remote Agent MCP Server to do?

Each tool has a stable name, a human-readable purpose, and a JSON input contract discovered during MCP initialization. Risk classes come from the project’s registry manifest when one is available.

11 named tools

fetch_agent_card

Fetch /.well-known/agent-card.json from a remote agent

read only

validate_agent_card

Verify signature, version, auth, and capabilities of an agent card

read only

list_agents

Show configured remote agents

read only

send_task

Create or continue a remote A2A task

external write

send_task_streaming

Start remote task with streaming updates

external write

get_task

Fetch task state and history

read only

list_tasks

Page and filter remote task registry

read only

cancel_task

Cancel running remote task

external write

subscribe_events

Open SSE subscription for task events

read only

manage_push_notifications

Create, update, or delete push notification configs

internal write

get_agent_capabilities

Fetch private agent capabilities (extended card)

read only

Governance

Understand the effect of every tool.

A server connection inherits the authority of its credentials and deployment environment. The declarations below come from this project’s README and MCP registry manifest; your application still decides which tools an agent receives and where approval is required.

7 read only3 external write1 internal write

Protocol version validation — reject incompatible agents
Tenant-scoped auth — isolation headers for multi-tenant deployments
Remote task limits — rate limiting per agent
Audit logging — all A2A interactions recorded

MCP surface

What the current documentation declares.

MCP can carry tools, resources, prompts, structured results, progress, cancellation, and long-running work. This record highlights the modern protocol features explicitly mentioned by this repository.

Subscriptions

Long-running tasks

ADK MCP SDKrmcpRegistry manifest

Install and connect

Follow the project’s documented starting point.

Install the server in the environment that owns its credentials and domain access. Add it to your MCP host, verify the discovered tools, and narrow the toolset before giving it to a production agent.

Install

cargo install mcp-a2a

ADK-Rust connection shape

let toolset = McpToolset::from_stdio(
    "mcp-a2a",
    ["mcp-a2a"],
).await?;

let agent = LlmAgentBuilder::new("agent")
    .tools(toolset.tools().await?)
    .build()?;

Commands and configuration are extracted from the public README. Confirm prerequisites, environment variables, and release-specific options in the official documentation before deployment.

Official documentation

Continue with the project maintainers’ source of truth.

This page provides an approachable map of the server. The repository remains authoritative for exact schemas, prerequisites, configuration, examples, tests, releases, and security updates.