agentmail-toolkit

AgentMail Toolkit

Install the toolkit for the selected language and set AGENTMAIL_API_KEY.

npm install agentmail-toolkit
pip install agentmail-toolkit

The TypeScript and Python packages can expose different tool sets and can release on different schedules. Discover the installed package's tool catalog at runtime instead of trusting a hardcoded list:

new AgentMailToolkit().getTools().map((tool) => tool.name)

[tool.name for tool in AgentMailToolkit().get_tools()]

TypeScript

Vercel AI SDK

import { openai } from "@ai-sdk/openai";
import { streamText } from "ai";
import { AgentMailToolkit } from "agentmail-toolkit/ai-sdk";

const toolkit = new AgentMailToolkit();
const result = await streamText({
  model: openai(process.env.OPENAI_MODEL!),
  messages,
  system: "Use email tools only when the user authorizes the external action.",
  tools: toolkit.getTools(),
});

LangChain

import { createAgent } from "langchain";
import { AgentMailToolkit } from "agentmail-toolkit/langchain";

const agent = createAgent({
  model: process.env.LANGCHAIN_MODEL!,
  tools: new AgentMailToolkit().getTools(),
  systemPrompt: "Use email tools only when the user authorizes the external action.",
});

MCP server tools

import { AgentMailToolkit } from "agentmail-toolkit/mcp";

const tools = new AgentMailToolkit().getTools();

Each tool provides a name, title, description, input schema, output schema, callback, and complete annotations for registration on your own MCP server. On a successful call the MCP adapter returns structuredContent (validated against the output schema) alongside the JSON text block; on failure it returns an isError result. The Python package does not ship an MCP adapter.

Existing client

import { AgentMailClient } from "agentmail";
import { AgentMailToolkit } from "agentmail-toolkit/ai-sdk";

const client = new AgentMailClient({ apiKey: process.env.AGENTMAIL_API_KEY });
const toolkit = new AgentMailToolkit(client);