Reply.io for AI agents

Reply.io automates multichannel sales outreach, letting teams build sequences, connect email accounts, and track contact status across campaigns. 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 · REPLY.IOPOLICY: acme-support
09:41:07 · claude · u_8f2read
reply_io.list_lists
Reply.io List Lists✓ allowed · 212ms
09:41:08 · claude · u_8f2read
reply_io.list_sequences
List Sequences✓ allowed · 164ms
09:41:09 · claude · u_8f2write
reply_io.create_contact
Create Contact✓ approved · approved by user
09:41:12 · claude · u_8f2destructive
reply_io.delete_user
Delete User✕ blocked · policy: deny
EVERY REPLY.IO CALL, ON THE RECORD
01 · USE CASES

What agents do in Reply.io.

01

Add a contact to a sequence

Add a new lead to an outreach sequence after they're marked as a good fit.

02

Check a contact's status

Get a contact's current sequence status before deciding whether to follow up manually.

03

Confirm before deleting a sequence

Look up a sequence's steps and contacts first, then delete it only once approved.

02 · ACTIONS

33 Reply.io actions, graded by risk.

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

read

13

Look things up. Allowed by default.

  • reply_io.list_lists
    Reply.io List Lists
  • reply_io.list_sequences
    List Sequences
  • reply_io.search_contacts
    Search Contacts by Email
  • reply_io.get_current_user
    Get Current User
  • reply_io.get_contact_by_id
    Get Contact by ID
  • reply_io.get_contact_status
    Get Contact Status
  • reply_io.get_sequence_by_id
    Get Sequence By ID
  • reply_io.list_contacts_basic
    List Contacts Basic
  • reply_io.list_email_accounts
    Reply.io List Email Accounts
  • reply_io.list_sequence_steps
    List Sequence Steps
  • reply_io.get_sequence_step_by_id
    Get Sequence Step by ID
  • reply_io.get_sequence_contacts_extended
    Get Sequence Contacts Extended
  • reply_io.get_disconnected_email_accounts
    Reply.io Get Disconnected Email Accounts

write

11

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

  • reply_io.create_contact
    Create Contact
  • reply_io.update_contact
    Update Contact
  • reply_io.create_sequence_step
    Create Sequence Step
  • reply_io.update_email_account
    Update Email Account
  • reply_io.add_contact_to_sequence
    Add Contact to Sequence
  • reply_io.generate_ulid
    Generate ULID
  • reply_io.pause_sequence
    Pause Sequence
  • reply_io.start_sequence
    Start Sequence
  • reply_io.set_contact_status
    Set Contact Status
  • reply_io.connect_gmail_account
    Connect Gmail Account
  • reply_io.connect_exchange_account
    Connect Exchange Account via OAuth

destructive

9

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

  • reply_io.delete_user
    Delete User
  • reply_io.delete_contact
    Delete Contact
  • reply_io.delete_schedule
    Delete Schedule
  • reply_io.delete_sequence
    Delete Sequence
  • reply_io.archive_sequence
    Archive Sequence
  • reply_io.delete_email_account
    Delete Email Account
  • reply_io.remove_contact_from_sequence
    Remove Contact From Sequence
  • reply_io.remove_contacts_from_sequence
    Bulk Remove Contacts from Sequence
  • reply_io.clear_contact_status
    Clear Contact Status
03 · HOW IT WORKS

Reply.io in three steps.

  1. 01Your users connect Reply.ioThey add their Reply.io api key on Arc0 Connect, under your brand. It goes straight into the vault.
  2. 02You set the rulesReads run, writes like “create Contact” can wait for the user, and “delete User” can be denied outright.
  3. 03Any agent can actYour agent calls Reply.io 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_io', {
  read: 'allow',
  write: 'ask',        // create_contact
  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.io connects.

Users add their Reply.io 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.io 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.io from any agent.

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

Reply.io and Arc0, answered.

Q01

Can I use Reply.io with Claude, ChatGPT or Cursor?

Yes. Connect Reply.io 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.io actions you allow.

Q02

How do users connect Reply.io?

Users add their Reply.io 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.io actions can my agent take?

33 in total: 13 read, 11 write and 9 destructive, such as “create Contact”. Your policies decide which of them each agent may call.

Q04

Can I stop my agent from deleting things in Reply.io?

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.io too?

Yes. The same Reply.io 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.io into your agent.

Your users connect Reply.io once, under your brand. Your agent gets 33 actions behind your policies, with every call on the record.

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