Does this toolkit manage organization members, workspaces and API keys?

Not in its current form. Despite the name, the three actions exposed are Create Message, Get Model and List models. Adding members, editing workspaces and rotating API keys are not available through this integration and stay in the Anthropic Console.

Why list the models before sending a message?

Because model IDs change. List models is the correct source for them, and a stale ID passed to Create Message returns a not_found_error, so resolving the ID first is what keeps the call from failing outright.

What would Lyro actually use Create Message for?

A discrete generation step inside work it is already doing - drafting, classifying or summarising text - by sending the relevant user and assistant turns and taking Claude's response back. Lyro's own customer conversations do not depend on this connection.

Whose Anthropic account is billed for these calls?

Yours. Create Message runs against the API key you connect, so token usage lands on that organization's Anthropic account rather than being bundled into Lyro.

Anthropic administrator MCP integration

Lists the Claude models available on an account, retrieves one by ID, and sends a conversation history for a completion.

Connect Anthropic administrator See all integrations

3actions available

Three actions you can hand over today

Every action runs live through MCP. Nothing to build, nothing to maintain.

Create message
Lyro creates a message completion from Claude to answer complex questions. Support agents get AI-powered answers for customer queries without leaving the chat.
Get model
Lyro retrieves details about a specific AI model by model ID. Support agents can verify model availability and capabilities before using them.
List models
Lyro lists all available AI models from Anthropic. Support agents can see which models Lyro has access to for different tasks.

See all 3 actions

How businesses use Anthropic administrator + Lyro

Each card is one request a support team gets, and the Anthropic administrator actions Lyro runs to close it.

Run a completion against a current Claude model
Lyro lists the models available on the account, confirms the one it needs by ID, and sends the conversation history for a completion, so the call never depends on a hardcoded model ID.
List ModelsGet ModelCreate Message

How it works

Get started in 3 steps

Connect once, then just ask. There is no workflow builder to learn and nothing to maintain — Lyro reads the Anthropic administrator actions it has and picks the ones a request needs.

01
Connect Anthropic administrator
Authorize the Anthropic administrator account your team already uses — one consent screen, no API keys, no mapping tables. Lyro can only do what you granted that account, and you can disconnect it at any time.
02
Tell your agent what you need
Describe the job the way you would hand it to a teammate. Lyro maps it to the Anthropic administrator actions that close it and chains as many as the request needs.
03
Watch it work
The agent runs the actions inside the conversation the customer is already in, so nobody copies data between tabs and your team can take over at any point.
Get started free

Anthropic administrator · Lyro

Everything else about Anthropic administrator

Setup, permissions, and the limits of what Lyro can do inside Anthropic administrator.

Not in its current form. Despite the name, the three actions exposed are Create Message, Get Model and List models. Adding members, editing workspaces and rotating API keys are not available through this integration and stay in the Anthropic Console.