Customer.io

listing.by

Read and change Customer.io journeys, segments, people, content and data pipelines from your AI assistant.

state.auth.long (state.auth.title)Streamable HTTP

listing.connect

listing.explain.oauth

https://mcp.customer.io/mcp

listing.note.oauth

listing.share.h

listing.share.p

mcp.tc/i/customer-io

listing.about

Connects a Customer.io account to MCP-compatible AI tools such as Claude, ChatGPT and Cursor. You can read workspace data, create and manage automations and one-time sends, work with segments, and make other changes through natural language prompts.

Runs as a hosted streamable HTTP endpoint at https://mcp.customer.io/mcp for US accounts. EU accounts use https://mcp-eu.customer.io/mcp. Users sign in with OAuth, and an account admin must first enable MCP under Settings > AI. Requested scopes include read, write, configure, read:sensitive and write:live.

listing.can

  • Read workspace data such as people and segments
  • Create and manage automations and journeys
  • Create and manage one-time sends
  • Work with segments
  • Edit message content
  • Manage data pipelines

listing.tools

listing.notools.oauth

listing.prompts

  • List the segments in my Customer.io workspace.

  • Create a one-time send to my newsletter segment.

  • Show me the journeys that are currently live.

  • Find the person with email jane@example.com and show their attributes.

listing.setup.h

listing.setup.oauth

Claude Code

  1. Run this in a terminal, in your project folder:
claude mcp add --transport http customer-io https://mcp.customer.io/mcp
  1. Start Claude Code, type /mcp, pick customer-io and choose Authenticate. A browser window opens for the Customer.io sign-in.

Add --scope user to make it available in every project, not just this one.

Claude Desktop

  1. Open Settings → Connectors and click Add custom connector.
  2. Name it Customer.io and paste this URL:
https://mcp.customer.io/mcp
  1. Click Add, then Connect, and sign in when Customer.io asks.

Claude Desktop's JSON config file only starts local servers. Remote servers go through Connectors, and connectors you add on claude.ai show up here too.

claude.ai

  1. Open the connector form on claude.ai. This button fills in the name and URL for you:
  1. Check that the URL reads https://mcp.customer.io/mcp and click Add.
  2. Click Connect and sign in when Customer.io asks.

Free plans allow one custom connector. On Team and Enterprise plans an owner adds it under Organization settings → Connectors.

ChatGPT

  1. On chatgpt.com, open Settings → Security and login and turn on Developer mode.
  2. Go to chatgpt.com/plugins and click + to create an app for a remote MCP server.
  3. Paste https://mcp.customer.io/mcp as the server URL and choose OAuth. ChatGPT sends you to Customer.io to sign in.

Developer mode is available on the web for Plus, Pro, Business, Enterprise and Education accounts.

Cursor

Or add it by hand to ~/.cursor/mcp.json (all projects) or .cursor/mcp.json (this project):

mcp.json
{
  "mcpServers": {
    "customer-io": {
      "url": "https://mcp.customer.io/mcp"
    }
  }
}

Cursor shows Needs login next to the server. Click it to sign in.

VS Code

Or from a terminal:

code --add-mcp '{"name":"customer-io","type":"http","url":"https://mcp.customer.io/mcp"}'

Or commit it to the repo in .vscode/mcp.json:

.vscode/mcp.json
{
  "servers": {
    "customer-io": {
      "type": "http",
      "url": "https://mcp.customer.io/mcp"
    }
  }
}

VS Code asks you to sign in the first time the server starts.

Devin Desktop

  1. Add it to ~/.config/devin/mcp_config.json (macOS and Linux) or %APPDATA%\devin\mcp_config.json (Windows):
mcp_config.json
{
  "mcpServers": {
    "customer-io": {
      "serverUrl": "https://mcp.customer.io/mcp"
    }
  }
}
  1. Refresh the MCP server list in Cascade and sign in when asked.

Devin Desktop is the new name for Windsurf. It reads serverUrl (or url) for remote servers.

Codex

codex mcp add customer-io --url https://mcp.customer.io/mcp
codex mcp login customer-io

Or edit ~/.codex/config.toml directly:

config.toml
[mcp_servers.customer-io]
url = "https://mcp.customer.io/mcp"

Gemini CLI

gemini mcp add --transport http customer-io https://mcp.customer.io/mcp

Then, inside Gemini CLI, run /mcp auth customer-io to sign in.

This adds it to the current project. Add -s user to use it everywhere.

Any client

Most clients accept this shape. Some name the URL field differently: serverUrl in Devin Desktop, httpUrl in Gemini CLI's settings file.

{
  "mcpServers": {
    "customer-io": {
      "type": "http",
      "url": "https://mcp.customer.io/mcp"
    }
  }
}

Zed puts servers under context_servers in its settings. Cline needs "type": "streamableHttp", or it assumes SSE.

Client only starts local servers? Bridge it with npx -y mcp-remote https://mcp.customer.io/mcp.

listing.faq

Can I paste mcp.tc/i/customer-io into my MCP client?

No. mcp.tc links are pages, not server addresses. Connect with https://mcp.customer.io/mcp, so your client talks to Customer.io directly. The sign-in token only works there anyway. The quick link is for sharing: it opens this page, with setup steps for every client.

Does Customer.io need an API key or a sign-in?

Yes, you need a Customer.io account. The first time your client connects, it opens Customer.io's sign-in page. The token goes straight to the server's own URL, never through mcp.tc.

Is Customer.io a remote or a local server?

Remote. Customer.io hosts it at https://mcp.customer.io/mcp, and it speaks Streamable HTTP. There's nothing to install.

What can Customer.io do?

You can read workspace data such as people and segments, create and manage automations and journeys and create and manage one-time sends.

Which clients can use it?

Any client that supports remote MCP servers: Claude Code, Claude Desktop, claude.ai, ChatGPT in developer mode, Cursor, VS Code, Devin Desktop, Codex, Gemini CLI, Zed and others. The setup steps cover each one.

Who wrote this page?

mcp.tc's robot read Customer.io's own metadata (its MCP handshake, tool list and public pages), and an AI model drafted the text from it. A person reviews anything the checks can't confirm. The text can still be wrong, so if you spot a mistake, use Report this listing on this page.

listing.em.h

listing.em.lead listing.em.how

listing.em.badge

em.prev_lightem.prev_dark
Markdown
[![Customer.io on mcp.tc](https://mcp.tc/i/customer-io/badge.svg)](https://mcp.tc/i/customer-io)
HTML
<a href="https://mcp.tc/i/customer-io"><img src="https://mcp.tc/i/customer-io/badge.svg" alt="Customer.io on mcp.tc" height="20"></a>

listing.em.badge_note

listing.em.widget

HTML
<script src="https://mcp.tc/w/customer-io.js" async></script>

listing.em.widget_note

iframe

HTML
<iframe src="https://mcp.tc/embed/customer-io" title="Customer.io on mcp.tc" width="420" height="200" loading="lazy" allow="clipboard-write" style="border:0;border-radius:8px;max-width:100%"></iframe>

listing.em.iframe_note

JSON

listing.em.json

https://mcp.tc/i/customer-io.json

listing.em.fields

listing.disclaimer_checked