Give Your LangChain Agents Email Superpowers

Connect LangChain's tool-calling agents to MultiMail for sending, reading, and managing email — with configurable human oversight at every step.

LangChain is the most widely adopted framework for building LLM-powered applications. Its agent system supports tool calling, allowing models to interact with external services like email. MultiMail provides the email infrastructure layer that LangChain agents need to send, receive, and manage messages on behalf of users.

By integrating MultiMail with LangChain, your agents can compose and send emails, check inboxes, manage contacts, and handle threads — all while respecting human oversight boundaries. The default gated_send mode means your agent drafts emails but a human approves before delivery, building trust incrementally.

You can connect LangChain to MultiMail using the MCP server (@multimail/mcp-server) for native tool integration, or call the REST API directly using custom tools. Both approaches give your agents access to the full suite of email capabilities.

Why MultiMail

Built for LangChain developers

Built for Agents, Not Humans

MultiMail's API is designed for programmatic access. Every action — sending, reading, replying — is an API call your LangChain agent can invoke as a tool, with structured inputs and outputs.

Graduated Trust via Oversight Modes

Start with gated_send (agent composes, human approves) and progress to monitored or autonomous as trust builds. LangChain agents can query their current oversight level and adapt behavior accordingly.

MCP Server Integration

The @multimail/mcp-server package exposes email tools in the Model Context Protocol format. LangChain's MCP tool adapter lets your agent call send_email, check_inbox, and other tools natively.

Thread-Aware Conversations

MultiMail tracks email threads automatically. Your LangChain agent can retrieve full conversation history with get_thread, making context-aware replies natural.

Contact Management

Agents can search and manage contacts through manage_contacts and manage_contacts tools, enabling relationship-aware email workflows within your LangChain chains.

Try it

Try it with your agent

No code, no dashboard. Paste this to your AI agent — it connects MultiMail, creates an inbox, and builds the flow for you.

1. Get MultiMail ready: read https://multimail.dev/llms.txt, follow its MCP connection instructions exactly, connect the MultiMail MCP server to this agent environment, create a free inbox, and set up a verified sending domain or sender before attempting to send anything. 2. Wire MultiMail into LangChain using LangChain's real tool mechanism: load the MultiMail MCP tools with the official LangChain MCP adapter, pass the resulting tools into a LangChain tool-calling agent, and do not invent direct MultiMail HTTP calls, API paths, headers, or custom wrapper methods. 3. Give the LangChain agent only the MultiMail capabilities exposed by the connected MCP server: checking the inbox, composing or drafting replies, and sending or scheduling email from the verified sender. Use the actual tool names returned by the MCP server. 4. Send a test email from the verified sender to an address I provide, then check the inbox for replies and draft a concise response without sending it automatically. 5. Run MultiMail in gated_send oversight mode for this setup, so every outbound email or scheduled send is presented for developer review and approval before it leaves the system.
Getting started

Step by step

1

Create a MultiMail Account and API Key

Sign up at multimail.dev, create a mailbox, and generate an API key from your dashboard. Your key will start with mm_live_.

2

Install Dependencies

Install LangChain and the HTTP library for calling the MultiMail API.

3

Define Your Email Tools

Create LangChain @tool functions that wrap MultiMail API endpoints. At minimum, define send_email and check_inbox tools.

4

Create and Run Your Agent

Build a tool-calling agent with a system prompt that explains the email context and oversight mode. Run it with AgentExecutor.

5

Approve Pending Emails

If your mailbox uses gated_send mode (the default), review and approve pending emails in the MultiMail dashboard before they are delivered.

FAQ

Common questions

Does LangChain have a native MultiMail integration?
There is no official langchain-multimail package. You integrate MultiMail by either defining custom @tool functions that call the REST API, or by connecting to the @multimail/mcp-server via LangChain's MCP adapter. Both approaches give your agent full access to MultiMail's email tools.
What happens when my agent sends an email in gated_send mode?
In gated_send mode, the API returns a success response with a pending status. The email is queued for human review in the MultiMail dashboard. Once approved, it is delivered. Your agent can check the status of pending emails using the list_pending tool or API endpoint.
Can I use LangChain's async features with MultiMail?
Yes. The MultiMail REST API works with any HTTP client, so you can use aiohttp or httpx for async requests. If you use the MCP server integration, the MCP client adapter already supports async operations natively through LangChain's ainvoke pattern.
How do I handle email attachments?
The MultiMail API supports attachments via the send and reply endpoints. Pass attachments as base64-encoded content in the request body. Your LangChain tool can accept file paths, encode them, and include them in the API call.
Can my LangChain agent manage multiple mailboxes?
Yes. Use the list_mailboxes tool or GET /mailboxes endpoint to discover available mailboxes. Your agent can then route emails through specific mailboxes by passing the appropriate mailbox_id to send and inbox tools. This is useful for agents handling different departments or personas.
Is there rate limiting on the MultiMail API?
Rate limits depend on your plan tier. The Starter (free) plan allows 200 emails per month, while paid plans range from 5,000 to 150,000. The API returns standard 429 responses when limits are reached, which your LangChain agent can handle with retry logic.
Related integrations

Explore more

LangGraph

orchestration · both

View guide →

CrewAI

multi-agent · python

View guide →

LlamaIndex

rag · both

View guide →

LangFlow

workflow · python

View guide →
Get started

The only agent email with a verifiable sender

Email infrastructure built for AI agents. Verifiable identity, graduated oversight, and a hosted MCP server. Formally verified in Lean 4.

Read the Docs →See Pricing