AgentMail Toolkit

AgentMail is an inbox-as-an-API platform for AI agents. The langchain-agentmail package provides LangChain tools for sending messages, replying inside a thread, managing drafts, downloading attachments, and labeling—all wired to a real AgentMail inbox.

Overview

Integration details

Class	Package	Serializable	JS support	Version
`AgentMailToolkit`	`langchain-agentmail`	❌	❌

Available tools

Tool	Description
`AgentMailListInboxesTool`	List inboxes on the account
`AgentMailCreateInboxTool`	Create a new inbox
`AgentMailListThreadsTool`	List threads inside an inbox
`AgentMailGetThreadTool`	Fetch a thread with its messages
`AgentMailListMessagesTool`	List messages inside an inbox
`AgentMailGetMessageTool`	Fetch a single message with its body
`AgentMailSendTool`	Send a new email from an inbox
`AgentMailReplyTool`	Reply inside an existing thread
`AgentMailUpdateMessageLabelsTool`	Add or remove labels on a message
`AgentMailCreateDraftTool`	Stage a draft (with optional `send_at` for scheduled delivery)
`AgentMailUpdateDraftTool`	Revise an existing draft
`AgentMailSendDraftTool`	Send a previously created draft
`AgentMailDeleteDraftTool`	Permanently delete a draft
`AgentMailGetAttachmentTool`	Get a presigned download URL for a message attachment

Setup

Install the package:

pip install -qU langchain-agentmail

Credentials

You need an AgentMail API key. Sign up at agentmail.to to get one.

import getpass
import os

if not os.environ.get("AGENTMAIL_API_KEY"):
    os.environ["AGENTMAIL_API_KEY"] = getpass.getpass("AgentMail API key:\n")

Instantiation

Use the toolkit to get all tools at once:

from langchain_agentmail import AgentMailToolkit

toolkit = AgentMailToolkit.from_api_key()
tools = toolkit.get_tools()

You can also instantiate individual tools directly:

from langchain_agentmail import AgentMailSendTool, AgentMailReplyTool

send = AgentMailSendTool()
reply = AgentMailReplyTool()

Invocation

Invoke directly with args

from langchain_agentmail import AgentMailSendTool

tool = AgentMailSendTool()
result = tool.invoke({
    "inbox_id": "ib_abc123",
    "to": "alice@example.com",
    "subject": "Hello from LangChain",
    "text": "This message was sent through langchain-agentmail.",
})
print(result)

Invoke with ToolCall

model_generated_tool_call = {
    "args": {
        "inbox_id": "ib_abc123",
        "to": "alice@example.com",
        "subject": "Follow up",
        "text": "Just checking in.",
    },
    "id": "1",
    "name": "agentmail_send_message",
    "type": "tool_call",
}
tool_msg = tool.invoke(model_generated_tool_call)
print(tool_msg.content)

Use within an agent

from langchain_agentmail import AgentMailToolkit
from langchain.chat_models import init_chat_model
from langgraph.prebuilt import create_react_agent

model = init_chat_model(model="claude-sonnet-4-6", model_provider="anthropic")

toolkit = AgentMailToolkit.from_api_key()
agent = create_react_agent(model, toolkit.get_tools())

response = agent.invoke({
    "messages": [(
        "user",
        "Check my inbox for anything new. Summarize the most recent thread in 2 sentences.",
    )]
})

Drafts

The draft tools let an agent compose iteratively, revise, and ship—useful when a model wants to stage a message and confirm before sending, or schedule delivery via send_at:

from langchain_agentmail import (
    AgentMailCreateDraftTool,
    AgentMailUpdateDraftTool,
    AgentMailSendDraftTool,
)

created = AgentMailCreateDraftTool().invoke({
    "inbox_id": "ib_abc123",
    "to": "alice@example.com",
    "subject": "Draft v1",
    "text": "First pass — will be revised before sending.",
})

# `created` is a JSON string; parse to get the draft_id
import json
draft_id = json.loads(created)["draft_id"]

AgentMailUpdateDraftTool().invoke({
    "inbox_id": "ib_abc123",
    "draft_id": draft_id,
    "subject": "Draft v2 — ready",
    "text": "Revised body. Sending now.",
})

AgentMailSendDraftTool().invoke({
    "inbox_id": "ib_abc123",
    "draft_id": draft_id,
})

Attachments

Outbound attachments can be passed as base64 file content or as a public URL. Inbound attachments are fetched via presigned download URLs:

import base64
from langchain_agentmail import AgentMailSendTool, SendAttachmentSpec

AgentMailSendTool().invoke({
    "inbox_id": "ib_abc123",
    "to": "alice@example.com",
    "subject": "Report attached",
    "text": "See the attached file.",
    "attachments": [
        SendAttachmentSpec(
            filename="report.txt",
            content_type="text/plain",
            content=base64.b64encode(b"hello").decode(),
        )
    ],
})

API reference

For detailed documentation of the AgentMail API, visit docs.agentmail.to. The Python package source lives at github.com/agentmail-to/langchain-agentmail.

Connect these docs to Claude, VSCode, and more via MCP for real-time answers.

Edit this page on GitHub or file an issue.

Popular Providers

Integrations by component

Overview

Integration details

Available tools

Setup

Credentials

Instantiation

Invocation

Invoke directly with args

Invoke with ToolCall

Use within an agent

Drafts

Attachments

API reference

​Overview

​Integration details

​Available tools

​Setup

​Credentials

​Instantiation

​Invocation

​Invoke directly with args

​Invoke with ToolCall

​Use within an agent

​Drafts

​Attachments

​API reference

Overview

Integration details

Available tools

Setup

Credentials

Instantiation

Invocation

Invoke directly with args

Invoke with ToolCall

Use within an agent

Drafts

Attachments

API reference