The Loops connector.
Contacts, lists and transactional email. Connect once with your own key. Every agent your team runs reads the same 5 tools under one permission model.
How access is governed
5
Read tools
Open by default. They run when called, and every call is logged with the endpoint, tool and capability.
0
Write tools
Loops exposes no write tools. Nothing it does mutates external state.
0
Destructive tools
Loops defines no destructive tools. Nothing here deletes data.
Defaults come from the capability on each tool definition, and an admin can tighten or open any tool individually. The endpoint's capability ceiling can only tighten that policy. An endpoint scoped to read never surfaces a write tool.
Every Loops tool
5 tools, named as the agent sees them.
- find_contactread
Find one contact by email address or by your own userId, and see their subscription state and which mailing lists they are on. Exactly one of `email` or `userId` — Loops rejects both. Returns an empty array when nobody matches.
- list_mailing_listsread
List the account's mailing lists. The `id` of a list is the key used in a contact's `mailingLists` map from find_contact, so use this to turn those ids into names.
- list_campaignsread
List campaigns, most recently created first, with their status and which mailing list or audience segment each targets. Reporting and inventory only; it does not send anything.
- list_transactional_emailsread
List the transactional emails defined in the account, newest first, including the data variables each template expects. Use it to find the right transactional id and to check what payload a template needs.
- list_contact_propertiesread
List the contact properties available on contacts — their key, human label and type. Pass list: "custom" for only the properties this account defined. Use it before reasoning about a property name you saw on a contact.
Use it from any agent
The same Loops tools reach Claude Code, Cursor, Claude Desktop or your own agent through one MCP endpoint. The endpoint is scoped to a group, the token is issued per group and revocable from the dashboard, and an allowed-tool list and capability ceiling limit what it exposes. Reads run. Gated writes refuse unless an admin opens them. Destructive tools remain unavailable over MCP.
{
"mcpServers": {
"growth": {
"type": "http",
"url": "https://app.notara.ai/mcp/g/acme/growth",
"headers": {
"Authorization": "Bearer ntr_mcp_xxxxxxxxxxxxxxxxxxxx"
}
}
}
}The URL and token are placeholders. Real endpoints are issued per group from the dashboard.
Setup
- 01
Create a Loops API Key in your Loops account (where to find it). The key is yours: Notara stores it encrypted and never sees a bill.
- 02
Paste it into the Notara dashboard. Credentials can be scoped to the workspace or to one person.
- 03
The tools appear with their capability defaults already set. Tighten or open any of them per tool, then invite the agent to a channel or issue an MCP token.
Connect Loops once. Use it everywhere.
Use Notara directly, or bring us the workflow that needs to be redesigned and built.