Get started

Sendloop for AI agents

Sendloop is an email marketing tool for small businesses, SaaS companies, and ecommerce sellers to manage subscriber lists and send campaigns. It reports on list and campaign performance. Connect it once through Arc0, and your agent, or Claude, ChatGPT and Cursor, can use it through one MCP endpoint, limited to what each user approved.

Connect SendloopSee the 5 actions ↓
MarketingOAuth 2.0MCP + RESTsendloop.com
AUDIT LOG · SENDLOOPPOLICY: acme-support
09:41:07 · claude · u_8f2read
sendloop.list_lists
List SendLoop Lists✓ allowed · 212ms
09:41:08 · claude · u_8f2read
sendloop.list_campaigns
List Campaigns✓ allowed · 164ms
EVERY SENDLOOP CALL, ON THE RECORD
01 · USE CASES

What agents do in Sendloop.

01

Check overall list performance

Pull the overall list report to see open and click trends before planning the next campaign.

02

List active campaigns

Retrieve every campaign currently running so a marketer can spot gaps or overlaps.

03

Look up subscriber counts

List the subscribers on a given Sendloop list before deciding who to include in a new send.

02 · ACTIONS

5 Sendloop actions, graded by risk.

Every Sendloop action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.

read

5

Look things up. Allowed by default.

  • sendloop.list_lists
    List SendLoop Lists
  • sendloop.list_campaigns
    List Campaigns
  • sendloop.get_account_info
    Get Sendloop Account Information
  • sendloop.list_subscribers
    List SendLoop Subscribers
  • sendloop.get_overall_list_report
    Get Overall List Report

write

0

Create and change things. Allow, or ask the user first.

  • No write actions.

destructive

0

Delete, cancel or archive. Ask first, or deny outright.

  • No destructive actions.
03 · HOW IT WORKS

Sendloop in three steps.

  1. 01Your users connect SendloopThey sign in to Sendloop on Arc0 Connect, under your brand, and approve the access you ask for.
  2. 02You set the rulesReads run, and writes like “updates” can wait for the user to approve.
  3. 03Any agent can actYour agent calls Sendloop through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
POLICY.TS
await arc0.policies.set('sendloop', {
  read: 'allow',
  write: 'ask',        
  destructive: 'deny',  
})

# Claude Code: the same connection, one URL
$ claude mcp add --transport http arc0 \
    https://mcp.arc0.ai/u/u_8f2
04 · AUTH AND DATA

How Sendloop connects.

Users sign in to Sendloop on Arc0 Connect and approve the scopes you request. Build with Arc0’s Sendloop OAuth app, or bring your own so the Sendloop consent screen names you. Tokens refresh automatically, and you can export them whenever you want.

The same Sendloop connection serves your agent over MCP and your own backend over REST and the proxy, so a user connects once. How Arc0 handles credentials →

AUTH
API key · OAuth 2.0
CREDENTIALS
Per-tenant encrypted vault
MODEL SEES
Results only, never credentials
AUDIT LOG
Every call, on every plan
05 · WORKS WITH

Use Sendloop from any agent.

Claude
ChatGPT
Cursor
Codex
VS Code
OpenAI Agents SDK
Claude Agent SDK
Vercel AI SDK
Mastra
LangGraph
06 · RELATED

More marketing apps.

Meta Ads67 actionsActiveCampaign298 actionsActiveTrail159 actionsAdobe Marketing Agent12 actionsAdtraction22 actionsAdyntel8 actionsAhrefs40 actionsAirOps96 actions
ALL MARKETING APPS →
07 · FAQ

Sendloop and Arc0, answered.

Q01

Can I use Sendloop with Claude, ChatGPT or Cursor?

Yes. Connect Sendloop to Arc0 once, then add your Arc0 MCP URL to Claude, ChatGPT, Cursor, Claude Code or any other remote-MCP client. Each assistant only gets the Sendloop actions you allow.

Q02

How do users connect Sendloop?

Users sign in to Sendloop on Arc0 Connect and approve the scopes you request. Build with Arc0’s Sendloop OAuth app, or bring your own so the Sendloop consent screen names you. Tokens refresh automatically, and you can export them whenever you want.

Q03

Which Sendloop actions can my agent take?

5 in total: 5 read, 0 write and 0 destructive. Your policies decide which of them each agent may call.

Q04

Can I make my agent read-only in Sendloop?

Yes. Allow read actions and deny writes in the Sendloop policy. Your agent can still look things up, and any write it attempts is blocked and logged.

Q05

Can my own backend call Sendloop too?

Yes. The same Sendloop connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.

Get started

Plug Sendloop into your agent.

Your users connect Sendloop once, under your brand. Your agent gets 5 actions behind your policies, with every call on the record.

Connect SendloopBrowse all apps →

Free to build · MCP + REST · Audit log on every plan