Developer toolsPublic source

MCP Registry

Central control plane for MCP server registration, tool discovery, allow-lists, health monitoring, and audit — for ADK-Rust Enterprise.

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 registry capabilities through a typed MCP contract.

Architecture

How MCP Registry 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.

→

MCP Registry

Validates the request and owns 10 documented tool contracts.

→

Domain system

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

Connection: stdio · Server framework: ADK MCP SDK + rmcp

MCP Registry architecture diagram from its official repository

Tool catalog

What can an agent ask MCP Registry 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.

10 named tools

register_server

Add a new MCP server definition

internal write

update_server

Edit command, URL, transport, credentials, or policy labels

internal write

list_servers

Return registered servers by environment, status, owner, or domain

read only

inspect_server

Inspect one server, including exposed tools and health

read only

discover_tools

Pull tool definitions from a server

read only

allow_list_tools

Approve which discovered tools agents can use

internal write

health_check

Run connectivity and schema checks

read only

restart_server

Restart local or managed server runtime

internal write

disable_server

Remove server from active agent routing

internal write

export_inventory

Export server, tool, credential, and policy inventory

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.

5 internal write5 read only

Production allow-list changes require policy simulation
Write-capable tool exposure requires Platform Admin approval
All mutations are audit-logged
Credential bindings reference vault entries only

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.

Resources

Prompts

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-registry

ADK-Rust connection shape

let toolset = McpToolset::from_stdio(
    "mcp-registry",
    ["mcp-registry"],
).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.

Overview ↗README.md CHANGELOG ↗CHANGELOG.md Api Reference ↗docs/api-reference.md Architecture ↗docs/architecture.svg Issues and support ↗github.com issues

Keep exploring