How to Use the Hiver MCP in LangChain

Q: How do I initialize Hiver with LangChain?

Install the langchain-mcp-adapters package. Pass your connection details to the multi-server client and grab the tools to inject into your ReAct agent.

Q: Can my LangChain agent see all shared inboxes in Hiver?

Yes, as long as the token has permissions. The agent runs listsharedinboxes to map out available mailboxes before attempting to read specific threads.

Build ReAct agents in LangChain that read email threads and draft team replies directly inside your Gmail helpdesk.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Hiver MCP to LangChain

Create your Vinkius account to connect Hiver 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 Hiver with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain email resolution in LangChain

Hiver lives right inside Gmail, but your agents need a way to read and interact with those shared inboxes. You build MCP chains that start with `list_inbox_conversations` to pull active threads. The agent parses the text, decides what needs attention, and moves to the next step. Output from that first tool feeds directly into `get_conversation_details` for deep context. If a human needs to step in, the agent runs `create_shared_draft` to tee up a response. You track every token and latency spike in LangSmith while the agent handles the heavy lifting.

Connect this MCP Server to your helpdesk

Setting up authentication takes seconds. Run `test_hiver_auth` to verify your credentials before deploying your pipeline. Once connected, your ReAct agent has full access to the shared environment. Need to route an angry customer to a specific manager? The agent calls `search_team_members` to find the right person, then uses `update_thread_status` to assign the ticket. Everything happens without leaving the LangChain execution loop.

Automate tag management dynamically

Hardcoding labels breaks when support teams change their workflow. Instead, your agent calls `list_inbox_tags` to pull the live taxonomy straight from Hiver. It understands the current categorization rules before making any updates. If a specific issue spikes, the agent can hunt down the right label using `search_tags_by_name`. It grabs the ID and tags the thread. Your human agents just see organized Gmail folders, completely unaware a script did the sorting.

Setup guide

Set up Hiver 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 Hiver 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({
    "hiver-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 Hiver 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 Hiver. 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 Hiver 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 Hiver MCP in LangChain

Install the `langchain-mcp-adapters` package. Pass your connection details to the multi-server client and grab the tools to inject into your ReAct agent.

Yes, as long as the token has permissions. The agent runs `list_shared_inboxes` to map out available mailboxes before attempting to read specific threads.

Every tool invocation logs automatically. You will see exactly how long `get_inbox_details` took to execute and what JSON payload returned.

Use the built-in session methods to keep the connection stateful. This prevents the agent from losing track of thread IDs when jumping between reading context and drafting replies.

Vinkius isolates your instance in a V8 sandbox. Your agent pulls customer email threads and team drafts directly into memory, and the ephemeral MCP Server destroys all state the moment the execution 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