On this page
Guides / Use Met from Claude in 3 steps

Use Met from Claude in 3 steps

Connect Met to Claude without code or an API key and ask it to answer, look up and build. Also in Claude Code, Codex, Cursor and VS Code.

Updated View .md

Claude can work inside your Met account, and so can Claude Code, Codex, Cursor, VS Code or any assistant that speaks MCP. You write to it the way you would write to someone on your team («which chats haven't I answered?», «create an orders collection») and it does it in Met for you.

You don't need to code or create an API key: you paste an address, sign in to Met and approve the permissions.

Step 1 · Add Met as a connector

The Met server address is always the same:

https://api.met.meteor.com.co/api/v1/mcp

The connector name is met- followed by your workspace name, for example met-my-company. In Met, Settings → Developers → Connect assistant gives it to you ready to copy, along with the commands for each assistant. That way, if you manage several workspaces, you connect one per workspace: each connector signs in separately and they don't clash.

Where you paste it depends on your assistant.

Claude (web or desktop app)

In Settings → Connectors, tap Add custom connector, give it the name Met gives you (for example met-my-company) and paste the address. If your Claude account is Team or Enterprise, an Owner of the organization adds the connector for the whole team. You don't need to touch claude_desktop_config.json: that file is for local servers.

Claude Code

In the terminal, add Met for all your projects:

claude mcp add --transport http --scope user met-my-company https://api.met.meteor.com.co/api/v1/mcp

Then open Claude Code and type /mcp to sign in, or do it from the terminal with claude mcp login met-my-company. Replace met-my-company with the name Met gives you.

Codex

In the terminal, add Met and sign in. You no longer need mcp-remote:

codex mcp add met-my-company --url https://api.met.meteor.com.co/api/v1/mcp
codex mcp login met-my-company

VS Code

In the terminal, add Met. VS Code asks you to sign in the first time you use it:

code --add-mcp '{"name":"met-my-company","type":"http","url":"https://api.met.meteor.com.co/api/v1/mcp"}'

MCP server also has the button that installs it in one click.

Cursor

MCP server has the button that installs it in one click. If you'd rather do it by hand, add a new server in Settings → MCP, or paste this into .cursor/mcp.json:

{
  "mcpServers": {
    "met-my-company": { "url": "https://api.met.meteor.com.co/api/v1/mcp" }
  }
}

Other assistants

Any assistant that speaks remote MCP connects with the same address and the same name; ChatGPT, for example, adds it in Settings → Apps & Connectors, with developer mode on depending on your plan.

Step 2 · Sign in and approve the permissions

When you connect, your assistant opens a Met window. Sign in with your usual user and review the list of what the assistant will be able to do: read contacts, send messages, create flows, and so on. If you agree, tap Authorize.

Step 3 · Ask for what you need

Write in your own words. You don't need to know what each tool is called: the assistant picks the right one and, if there is no specific tool for what you ask, it looks up the Met operation that does it and uses it with the same permissions you approved.

For day-to-day work

For building

A new flow stays as a draft: the assistant builds it, can test a single step and asks you before publishing it. Until it is published, it doesn't trigger on its own.

For building your SDR (the Met that qualifies your leads, follows up with them and hands your team the ones that belong to it)

Follow-ups are changed in the flow's draft without touching the rest of its steps, and they start running when you publish. Handoff rules are checked against the Met's prompt: if the prompt cites a rule that isn't declared, the assistant tells you, because that handoff wouldn't happen and the chat would stay with the Met.

Creating contact fields is a new permission («Create, edit and delete contact fields and variables»). If you connected your assistant before November 21, 2026, disconnect Met and connect it again to approve it.

For your pages and presentations

The assistant reads the page's text —each answer box with the question next to it— and changes only the text: it doesn't move, delete or restyle anything. It doesn't publish either: it writes on pages that aren't published yet, and leaves a published one alone. The previous version stays in the page's history in case you want to go back.

What it asks you before doing

Some actions Met won't allow without your explicit confirmation: the assistant has to ask you first, and only goes ahead if you say yes.

What costs money

Every tool that spends says so, and the assistant warns you before using it:

Creating or editing Mets, flows, collections and records doesn't spend Energy. Neither does looking things up.

On top of that, your assistant can ask for your permission every time it is about to use a Met tool. You set that up in the assistant's own settings.

There is one thing the assistant won't do even if you ask: talk over your team. If a person is handling a chat —autopilot is off or paused, or the contact asked to talk to a human—, the message isn't sent and the assistant tells you so.

What you can't do from the assistant

If your plan expired, the assistant can keep looking things up (contacts, conversations, data), but it can't change anything until the account is up to date. It tells you so instead of trying over and over.

If something doesn't work