How to Use the AgentMail MCP in LangChain

Q: How do I connect the AgentMail MCP Server to LangChain?

Install the langchain-mcp-adapters package first. You initialize a MultiServerMCPClient pointing to the Vinkius endpoint, extract the tools with gettools(), and pass them straight into your agent constructor.

Q: Can my LangChain agent read email attachments using AgentMail?

Yes. The agent calls getattachment to download the file. Since the payload arrives as base64, you will need a small parsing step in your chain to decode it before handing it to a document loader.

Q: Does LangChain support multiple AgentMail inboxes at once?

Yes, it handles as many as you need. Your agent runs listinboxes to see every address tied to the API key, then passes the correct ID to the next step.

Build email-native ReAct agents in LangChain that read, route, and reply to messages autonomously.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect AgentMail MCP to LangChain

Create your Vinkius account to connect AgentMail to LangChain and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup AgentMail with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Tie the AgentMail MCP Server into LangChain workflows

ReAct agents need tools to actually do things outside the terminal. You hook up the `agentmail-mcp` server, and suddenly your agent can run `list_inboxes` to find its assigned address. It grabs the ID and starts polling for new messages without human intervention. The real power hits when you chain these actions together. Your pipeline pulls fresh emails, parses the text through an LLM to determine intent, and fires off `reply_to_message` if the user asked a simple question. Every step gets logged in LangSmith so you see exactly which tool fired.

Automate complex email parsing and routing

Reading text is one thing, but extracting files requires specific operations. When an invoice hits the inbox, your agent uses `list_threads` to spot the incoming message. It then runs `get_attachment` to pull the base64-encoded PDF payload. You pipe that decoded payload straight into a document loader within the same chain. The agent reads the parsed invoice data, drafts a summary, and uses `forward_message` to send the details to your accounting department.

Manage multiple inboxes dynamically

Hardcoding email addresses scales poorly when you run dozens of specialized chains. Give your agent the `create_inbox` tool and let it spin up dedicated addresses for specific tasks. You map a custom domain so the outbound emails look professional. Once a temporary project wraps up, the agent cleans up after itself. It triggers `delete_inbox` to wipe the address and all associated messages. You avoid paying for stale inboxes while keeping your architecture entirely stateless.

Setup guide

Set up AgentMail MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes AgentMail tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "agentmail-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent AgentMail transactions"
    })
    print(result["messages"][-1].content)

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by AgentMail. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect AgentMail now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about AgentMail MCP in LangChain

Install the `langchain-mcp-adapters` package first. You initialize a `MultiServerMCPClient` pointing to the Vinkius endpoint, extract the tools with `get_tools()`, and pass them straight into your agent constructor.

Yes. The agent calls `get_attachment` to download the file. Since the payload arrives as base64, you will need a small parsing step in your chain to decode it before handing it to a document loader.

Every interaction gets logged automatically. You see the exact inputs your chain passed to `send_message` and the raw JSON response it got back.

Yes, it handles as many as you need. Your agent runs `list_inboxes` to see every address tied to the API key, then passes the correct ID to the next step.

Vinkius runs this MCP server inside an isolated V8 sandbox. When your agent pulls thread contents or base64 attachments, that sensitive payload routes through a zero-trust, ephemeral environment. Nothing persists on the intermediary layer after the request finishes.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript