Replyz / Claude Code

Give Claude Code its own email inbox.

Claude Code gets an address of its own. It signs up for the services your project needs, reads verification codes and links, and checks inboxes for you, without touching your personal email.

Get early access The skill on GitHub

How do you give Claude Code an email inbox?

Option 1: the skill (recommended)

Add the Replyz skill to your user skills, then ask Claude Code to get an inbox:

git clone https://github.com/replyz/skill ~/.claude/skills/replyz

"Get yourself a Replyz inbox, sign up at the service and tell me the code."

The skill runs the Replyz CLI, which signs up, creates the inbox and waits for email:

npx -y @replyz/cli signup --name claude-code
npx -y @replyz/cli inbox create --name signups
npx -y @replyz/cli wait --from "*@service.example" --otp

Option 2: the MCP server

claude mcp add --transport http replyz https://mcp.replyz.io/mcp \
  --header "Authorization: Bearer $REPLYZ_API_KEY"

See the Replyz MCP server for the full tool list.

How does Claude Code authenticate to Replyz?

With an API key in the REPLYZ_API_KEY environment variable. The CLI reads it on every command, so it is never pasted into the chat and the model never sees it. After sign-up, Claude Code sends you a claim link: one click ties the account to you and lifts the sandbox limits.

What can Claude Code do with its own inbox?

Sign up for dev services

Create accounts for the APIs and tools a project needs, and confirm them without you.

Test your sign-up flow

Read codes and links

One command returns the code or magic link from the right email.

Report back by email

Email you a summary when a long task finishes, and wait for your answer.

What can you ask Claude Code to do?

"Create a Replyz inbox for this project and sign up for the email API we need."
"Register a test user on staging and confirm the verification link works."
"Wait for the deploy notification email and tell me what it says."
"Email me when the migration is done, and wait for my go-ahead."

Is Claude Code an MCP client?

Yes. Claude Code can use MCP servers, including the Replyz one. For an agent running on your own machine, the skill and CLI are usually the better choice: a CLI call is one short line, uses less context, and keeps the key in the environment.

What is Claude Code?

Claude Code is Anthropic's agentic coding tool. It runs in your terminal or IDE, reads and edits code, runs commands, and can be extended with skills (folders with a SKILL.md file) and MCP servers.

Frequently asked questions

Can Claude Code have its own email address?

Yes. With the Replyz skill or CLI, Claude Code creates its own inbox in about a minute, with an address like name@youreplyz.com, and receives email there.

Should I use the skill, the CLI or MCP with Claude Code?

The skill with the CLI. Claude Code runs on your machine, so it can run CLI commands, which are fast and keep the API key out of the model's context. MCP also works if you prefer it.

How does Claude Code read a verification code?

It runs replyz wait with the sender and --otp, or calls get_verification through MCP. Replyz returns the code or link from the matching email, even if it arrived first.

Where does the API key go?

In the REPLYZ_API_KEY environment variable. The CLI reads it on each command, so it never appears in the conversation.

Can Claude Code send email from the inbox?

Only with your approval. It can email you and reply in threads someone started with it. Bulk, marketing and cold email are not allowed.