Communication
Missive for AI agents.
Managed auth, ready-made tools.
Read conversations, draft replies, add posts and manage contacts in Missive on behalf of each of your users.
About Missive
With the Missive connector, your agent works in each user’s own Missive inbox. It can list conversations, read their messages, write a draft reply, add a post to a conversation and look up or add contacts, using only the tools your project allows.
Missive is a collaborative inbox where a team shares email, chat and SMS conversations.
Tools
What your agent can do in Missive.
Each tool is a capability the model can call. You decide which ones a project allows, and every call runs with the end user's own Missive connection.
-
List conversations
Readmissive_list_conversationsList the conversations in the user's inbox.
-
Read a conversation
Readmissive_get_messagesRead the messages in a conversation.
-
Create a draft
Writemissive_create_draftWrite a draft reply in a conversation.
-
Add a post
Writemissive_create_postAdd a post to a conversation for the team to see.
-
List contacts
Readmissive_list_contactsList contacts from the user's contact books.
-
Create a contact
Writemissive_create_contactAdd a new contact to a contact book.
No tool matches that search.
Control
Limits you can set.
You decide what your agent may do in Missive, and Agent200 runs every call within those limits.
-
Turn single tools on or off
Let the agent read conversations and contacts, and switch off
missive_create_draftso it can never write a reply. -
Restrict what the agent reaches
Choose the endpoints and scopes a project may use, for example conversations but not contacts. A call outside them is refused.
Get started
Connect Missive
in three steps.
-
1
Set up the SDK
Add the Agent200 SDK to the codebase you already have and authenticate with your API key. The key covers every connector enabled for the project.
agent.jsConceptual exampleSet up the SDK with the Agent200 API key // One Agent200 API key covers every connector enabled for the project. const agent200 = new Agent200({ apiKey: process.env.AGENT200_API_KEY, }); -
2
Let your user connect Missive
Each end user authorizes their own Missive account once. Agent200 runs the OAuth flow, handles the callback, stores the tokens and refreshes them.
connect.jsConceptual exampleLet an end user connect their account (managed OAuth) // Each end user authorizes their own Missive account, once. const connection = await agent200 .user("user_123") .connect("missive"); if (connection.authorizationUrl) { // Show this link to your user; Agent200 handles the rest. console.log(connection.authorizationUrl); } -
3
Run with the Missive tools
Name the user, the model and the tools. The model decides which Missive tools to call, and Agent200 executes them with that user's connection.
run.jsConceptual exampleRun a request with the connector's tools const result = await agent200 .user("user_123") .run({ model: "openai/gpt-5.6-sol", input: "Summarize the open conversations in my Missive inbox", tools: ["missive"], }); console.log(result.output);
Access
Sign-in and permissions.
-
Who signs in
Each of your users, once, by connecting their own Missive account. Each connection is their own.
-
What access is requested
The connection acts with that user's access in Missive, such as reading conversations, writing drafts or managing contacts. Users can revoke it later from their Missive account settings.
For agents
Instructions for AI agents.
Using a coding agent? Paste this brief into it, or give it the address of this page. It describes the Missive connector and how to use it.
Connector: Missive, through Agent200. In code: "missive". What it does: Read conversations, draft replies, add posts and manage contacts in Missive on behalf of each of your users. Page: https://www.agent200.com/connectors/missive/ 1. Get an Agent200 API key. If the developer has none, send them to https://agent200.com/platform/apikeys/ and ask them to choose "Create an API key". Read the key from the AGENT200_API_KEY environment variable. Never ask for it in chat, and never write it into code, prompts or logs. 2. Sign-in is managed OAuth. Each end user approves access once, on Missive's own page, through the authorization link Agent200 returns. Never ask a user for a Missive password or token in chat. 3. Give every request a stable id for the end user. Agent200 uses only that user's own connection. 4. Read tools: missive_list_conversations, missive_get_messages, missive_list_contacts. Write tools: missive_create_draft, missive_create_post, missive_create_contact. Name "missive" in the tools of a request; the model decides which tool to call. 5. Stay within the project's settings. If a tool is turned off or a call is refused, tell the user. Do not work around it. 6. Before a write, confirm with the user, unless they asked for that exact change. 7. For setup with a specific framework, follow its guide: https://www.agent200.com/connectors/missive/framework/claude/ https://www.agent200.com/connectors/missive/framework/chatgpt/ https://www.agent200.com/connectors/missive/framework/claude-code/ https://www.agent200.com/connectors/missive/framework/muse/ https://www.agent200.com/connectors/missive/framework/grok-bot/ https://www.agent200.com/connectors/missive/framework/openai-dots/ https://www.agent200.com/connectors/missive/framework/claude-duet/ https://www.agent200.com/connectors/missive/framework/hermes-agent/ https://www.agent200.com/connectors/missive/framework/openclaw/ The code on the connector page is a conceptual example of the SDK. SDK reference: https://docs.igpt.ai/
This page is also available as Markdown, for agents and LLMs: /connectors/missive.md
Guides
Use Missive with the AI you build on.
Step-by-step setup for Missive with a specific model, assistant or agent framework.
-
Missive + Claude
How to connect Missive to Claude
-
Missive + ChatGPT
How to connect Missive to ChatGPT
-
Missive + Claude Code
How to connect Missive to Claude Code
-
Missive + Muse
How to connect Missive to Muse
-
Missive + Grok Bot
How to connect Missive to Grok Bot
-
Missive + OpenAI Dots
How to connect Missive to OpenAI Dots
-
Missive + Claude Duet
How to connect Missive to Claude Duet
-
Missive + Hermes Agent
How to connect Missive to Hermes Agent
-
Missive + OpenClaw
How to connect Missive to OpenClaw
FAQ
Missive and Agent200, answered.
Who handles the Missive OAuth flow and the tokens?
Agent200. It runs the authorization, handles the callback on its own domain, stores the tokens and refreshes them. You do not build or maintain an OAuth integration for Missive.
Does my agent act as the end user?
Within what that user authorized, yes. Every request names an end user, and Agent200 uses only that user's Missive connection, never another user's. It cannot reach anything the user or Missive has not authorized.
Can I limit what my agent can do in Missive?
Yes. You choose which services, endpoints and authorization scopes are allowed in your Agent200 configuration, and the agent works only within them.