carlyemail-toolkit

CarlyEmail's email tools for the OpenAI Agents SDK, LangChain, LiveKit Agents, and any other agent framework. A real inbox your agent can send, receive and reply from, without writing the tools yourself.

pip install "carlyemail-toolkit[openai]"     # or [langchain], [livekit]
export CARLYEMAIL_API_KEY=ce_us_...

from agents import Agent
from carlyemail_toolkit.openai import CarlyEmailToolkit

agent = Agent(
    name="Inbox",
    instructions="Read the thread before replying. Draft when unsure.",
    tools=CarlyEmailToolkit().get_tools(),
)

from langchain.agents import create_agent
from carlyemail_toolkit.langchain import CarlyEmailToolkit

agent = create_agent("openai:gpt-5-mini", CarlyEmailToolkit().get_tools())

from livekit.agents import Agent
from carlyemail_toolkit.livekit import CarlyEmailToolkit

agent = Agent(instructions="...", tools=CarlyEmailToolkit().get_tools())

from carlyemail_toolkit import CarlyEmailToolkit   # no framework

for tool in CarlyEmailToolkit().get_tools():
    tool.name, tool.description, tool.input_schema, tool.read_only
    tool(thread_id="...")                          # runs it

What is in it

The 26 tools the hosted MCP server serves — inboxes, threads, messages, drafts, attachments, labels, and account verification — with the same names, descriptions and parameter schemas, called over the REST API. Pass names to take only some:

tools = CarlyEmailToolkit().get_tools(["list_messages", "get_thread", "reply_to_message"])

A name that is not a tool raises rather than being dropped.

Which inbox

Every tool takes inbox_id, and most work without it. A key scoped to one inbox means that inbox. An organization with one inbox means that one. With several, the tools that read threads and drafts look across all of them, and every other tool refuses and names the inboxes so the agent can ask which — the same behaviour as the hosted server.

Errors

A failed call comes back to the model as one bounded line carrying the API's message and the fix it suggests — an Error: … tool result on the OpenAI Agents SDK, a handled ToolException on LangChain, a ToolError on LiveKit — so the agent can act on it next turn instead of the run ending.

See https://docs.carlyemail.com/integrations/toolkit.