Gmail toolkit integration

Integrate with the Gmail toolkit using LangChain Python.

This will help you get started with the Gmail toolkit. This toolkit interacts with the Gmail API to read messages, draft and send messages, and more. For detailed documentation of all GmailToolkit features and configurations head to the API reference.

Setup

To use this toolkit, you will need to set up your credentials explained in the Gmail API docs. Once you’ve downloaded the credentials.json file, you can start using the Gmail API.

Installation

This toolkit lives in the langchain-google-community package. We’ll need the gmail extra:

pip install -qU langchain-google-community\[gmail\]

To enable automated tracing of individual tools, set your LangSmith API key:

os.environ["LANGSMITH_TRACING"] = "true"
os.environ["LANGSMITH_API_KEY"] = getpass.getpass("Enter your LangSmith API key: ")

Instantiation

By default the toolkit reads the local credentials.json file. You can also manually provide a Credentials object.

from langchain_google_community import GmailToolkit

toolkit = GmailToolkit()

Customizing authentication

Behind the scenes, a googleapi resource is created using the following methods. you can manually build a googleapi resource for more auth control.

from langchain_google_community.gmail.utils import (
    build_resource_service,
    get_gmail_credentials,
)

# Can review scopes here https://developers.google.com/gmail/api/auth/scopes
# For instance, readonly scope is 'https://www.googleapis.com/auth/gmail.readonly'
credentials = get_gmail_credentials(
    token_file="token.json",
    scopes=["https://mail.google.com/"],
    client_secrets_file="credentials.json",
)
api_resource = build_resource_service(credentials=credentials)
toolkit = GmailToolkit(api_resource=api_resource)

Tools

View available tools:

tools = toolkit.get_tools()
tools

[GmailCreateDraft(api_resource=<googleapiclient.discovery.Resource object at 0x1094509d0>),
 GmailSendMessage(api_resource=<googleapiclient.discovery.Resource object at 0x1094509d0>),
 GmailSearch(api_resource=<googleapiclient.discovery.Resource object at 0x1094509d0>),
 GmailGetMessage(api_resource=<googleapiclient.discovery.Resource object at 0x1094509d0>),
 GmailGetThread(api_resource=<googleapiclient.discovery.Resource object at 0x1094509d0>)]

• GmailCreateDraft
• GmailSendMessage
• GmailSearch
• GmailGetMessage
• GmailGetThread

Use within an agent

Below we show how to incorporate the toolkit into an agent.

We will need a LLM or chat model:

# | output: false
# | echo: false

from langchain_openai import ChatOpenAI

llm = ChatOpenAI(model="gpt-5.4-mini", temperature=0)

from langchain.agents import create_agent


agent_executor = create_agent(llm, tools)

example_query = "Draft an email to [e-mail] thanking them for coffee."

stream = agent_executor.stream_events(
    {"messages": [("user", example_query)]},
    version="v3",
)
for snapshot in stream.values:
    snapshot["messages"][-1].pretty_print()

================================ Human Message =================================

Draft an email to [e-mail] thanking them for coffee.
================================== Ai Message ==================================
Tool Calls:
  create_gmail_draft (call_slGkYKZKA6h3Mf1CraUBzs6M)
 Call ID: call_slGkYKZKA6h3Mf1CraUBzs6M
  Args:
    message: Dear Fake,

I wanted to take a moment to thank you for the coffee yesterday. It was a pleasure catching up with you. Let's do it again soon!

Best regards,
[Your Name]
    to: ['[e-mail]']
    subject: Thank You for the Coffee
================================= Tool Message =================================
Name: create_gmail_draft

Draft created. Draft Id: r-7233782721440261513
================================== Ai Message ==================================

I have drafted an email to [e-mail] thanking them for the coffee. You can review and send it from your email draft with the subject "Thank You for the Coffee".

---

API reference

For detailed documentation of all GmailToolkit features and configurations head to the API reference.

---

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

Edit this page on GitHub or file an issue.