Missive for AI agents

Missive is a collaborative email and chat app that lets teams share inboxes, assign conversations, and manage tasks together in one interface. 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.

EmailAPI keyMCP + RESTmissiveapp.com
AUDIT LOG · MISSIVEPOLICY: acme-support
09:41:07 · claude · u_8f2read
missive.list_tasks
List Missive Tasks✓ allowed · 212ms
09:41:08 · claude · u_8f2read
missive.get_task
Get Missive Task✓ allowed · 164ms
09:41:09 · claude · u_8f2write
missive.create_post
Create Missive Post✓ approved · approved by user
09:41:12 · claude · u_8f2destructive
missive.delete_post
Delete Post✕ blocked · policy: deny
EVERY MISSIVE CALL, ON THE RECORD
01 · USE CASES

What agents do in Missive.

01

Look up a conversation

Pull a conversation's messages and comments to catch up before replying, read-only.

02

Create a draft reply

Create a draft response to a customer conversation for a teammate to review.

03

Approve before deleting a draft

Require approval before deleting a draft, since a colleague may still be working on it.

02 · ACTIONS

40 Missive actions, graded by risk.

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

read

21

Look things up. Allowed by default.

  • missive.get_task
    Get Missive Task
  • missive.list_tasks
    List Missive Tasks
  • missive.list_teams
    List Missive Teams
  • missive.list_users
    List Missive Users
  • missive.get_contact
    Get Missive Contact
  • missive.get_message
    Get Missive Message
  • missive.get_response
    Get Missive Response
  • missive.list_contacts
    List Missive Contacts
  • missive.list_messages
    List Messages by Message-ID
  • missive.list_responses
    List Missive Saved Responses
  • missive.get_conversation
    Get Missive Conversation
  • missive.list_contact_books
    List Missive Contact Books
  • missive.list_conversations
    List Missive Conversations
  • missive.list_organizations
    List Missive Organizations
  • missive.list_shared_labels
    List Missive Shared Labels
  • missive.list_contact_groups
    List Missive Contact Groups
+ 5 MORE

write

14

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

  • missive.create_post
    Create Missive Post
  • missive.create_task
    Create Missive Task
  • missive.create_team
    Create Team
  • missive.update_task
    Update Missive Task
  • missive.update_team
    Update Missive Team
  • missive.create_draft
    Create Draft
  • missive.create_webhook
    Create Webhook
  • missive.update_contact
    Update Missive Contact
  • missive.create_contacts
    Create Missive Contacts
  • missive.create_response
    Create Canned Response
  • missive.update_response
    Update Saved Response
  • missive.create_shared_label
    Create Shared Label
  • missive.update_shared_labels
    Update Shared Labels
  • missive.create_analytics_report
    Create Analytics Report

destructive

5

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

  • missive.delete_post
    Delete Post
  • missive.delete_draft
    Delete Draft
  • missive.delete_webhook
    Delete Webhook
  • missive.delete_responses
    Delete Saved Responses
  • missive.merge_conversations
    Merge Missive Conversations
03 · HOW IT WORKS

Missive in three steps.

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

# 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 Missive connects.

Users add their Missive 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 Missive 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 Missive from any agent.

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

Missive and Arc0, answered.

Q01

Can I use Missive with Claude, ChatGPT or Cursor?

Yes. Connect Missive 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 Missive actions you allow.

Q02

How do users connect Missive?

Users add their Missive 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 Missive actions can my agent take?

40 in total: 21 read, 14 write and 5 destructive, such as “create Missive Post”. Your policies decide which of them each agent may call.

Q04

Can I stop my agent from deleting things in Missive?

Yes. Actions like “delete Post” 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 Missive too?

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

Get started

Plug Missive into your agent.

Your users connect Missive once, under your brand. Your agent gets 40 actions behind your policies, with every call on the record.

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