Reply for AI agents

Reply.io is a sales engagement platform for running multichannel outreach sequences, tracking campaigns, contacts, and email accounts in one place. 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.

MarketingAPI keyMCP + RESTreply.io
AUDIT LOG · REPLYPOLICY: acme-support
09:41:07 · claude · u_8f2read
reply.list_campaigns
List Campaigns✓ allowed · 212ms
09:41:08 · claude · u_8f2read
reply.get_all_lists
Get All Lists✓ allowed · 164ms
09:41:09 · claude · u_8f2write
reply.create_list
Create Personal List✓ approved · approved by user
09:41:12 · claude · u_8f2destructive
reply.delete_user
Delete User✕ blocked · policy: deny
EVERY REPLY CALL, ON THE RECORD
01 · USE CASES

What agents do in Reply.

01

Move contacts between lists

Move a batch of contacts to a new list before starting a fresh outreach sequence.

02

Check the blacklist before a send

Get the full blacklist of domains and emails before adding a new list to a campaign.

03

Mark a contact as replied

Mark a contact as replied and finished once they respond, so the sequence stops emailing them.

02 · ACTIONS

21 Reply actions, graded by risk.

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

read

11

Look things up. Allowed by default.

  • reply.get_all_lists
    Get All Lists
  • reply.get_list_by_id
    Get List by ID
  • reply.list_campaigns
    List Campaigns
  • reply.search_contacts
    Search Contacts by Email
  • reply.get_blacklist_all
    Get full blacklist of domains and emails
  • reply.get_templates_list
    Get templates list
  • reply.list_contacts_basic
    List Contacts Basic
  • reply.list_email_accounts
    Reply.io List Email Accounts
  • reply.get_campaigns_for_contact
    Get Campaigns For Contact
  • reply.get_campaign_schedules_all
    Get all campaign schedules
  • reply.get_contacts_in_list_by_id
    Get Contacts in List by ID

write

5

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

  • reply.create_list
    Create Personal List
  • reply.generate_ulid
    Generate ULID
  • reply.move_contacts_to_lists
    Move Contacts to Lists
  • reply.mark_contact_as_replied
    Mark Contact as Replied
  • reply.mark_contact_as_finished
    Mark Contact As Finished

destructive

5

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

  • reply.delete_user
    Delete User
  • reply.delete_sequence
    Delete Sequence
  • reply.delete_list_by_id
    Delete List By ID
  • reply.delete_email_account
    Delete Email Account
  • reply.remove_domain_from_blacklist
    Remove Domain from Blacklist
03 · HOW IT WORKS

Reply in three steps.

  1. 01Your users connect ReplyThey add their Reply api key on Arc0 Connect, under your brand. It goes straight into the vault.
  2. 02You set the rulesReads run, writes like “create Personal List” can wait for the user, and “delete User” can be denied outright.
  3. 03Any agent can actYour agent calls Reply 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('reply', {
  read: 'allow',
  write: 'ask',        // create_list
  destructive: 'deny',  // delete_user
})

# 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 Reply connects.

Users add their Reply api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.

The same Reply 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
CREDENTIALS
Per-tenant encrypted vault
MODEL SEES
Results only, never credentials
AUDIT LOG
Every call, on every plan
05 · WORKS WITH

Use Reply from any agent.

Claude
ChatGPT
Cursor
Codex
VS Code
OpenAI Agents SDK
Claude Agent SDK
Vercel AI SDK
Mastra
LangGraph
07 · FAQ

Reply and Arc0, answered.

Q01

Can I use Reply with Claude, ChatGPT or Cursor?

Yes. Connect Reply 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 Reply actions you allow.

Q02

How do users connect Reply?

Users add their Reply api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.

Q03

Which Reply actions can my agent take?

21 in total: 11 read, 5 write and 5 destructive, such as “create Personal List”. Your policies decide which of them each agent may call.

Q04

Can I stop my agent from deleting things in Reply?

Yes. Actions like “delete User” are graded destructive. Set destructive actions to deny, or to ask so the user approves each one, and blocked calls still show up on the audit log.

Q05

Can my own backend call Reply too?

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

Get started

Plug Reply into your agent.

Your users connect Reply once, under your brand. Your agent gets 21 actions behind your policies, with every call on the record.

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