How to Use the Chanty MCP in LangChain

Build multi-step chat pipelines for LangChain using the Chanty MCP Server to automate your team communications.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Chanty MCP to LangChain

Create your Vinkius account to connect Chanty 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 Chanty with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain together Chanty message workflows

Pipe `send_message` outputs directly into your next reasoning step within LangChain. You define the logic flow, letting your agent handle repetitive communication tasks without manual oversight. Since every tool call functions as a link in your chain, you keep full observability over latency and token usage via LangSmith. Use `list_conversations` to feed context into the chain before the agent decides the next move.

Manage your team structure via LangChain

Query your workspace directory using `list_members` to map out active users. Your agent can then trigger `invite_member` based on specific project triggers you set up in your code. This gives your agent the ability to act on real-time organizational data. It stops the agent from guessing who belongs in a room and lets it rely on the actual Chanty directory.

Automate room lifecycle management

Deploy `create_conversation` to bootstrap new workspaces whenever your LangChain agent hits a specific project milestone. It keeps your communications organized as your pipeline progresses. When a project finishes, have your agent run `delete_conversation` to clean up the workspace. This keeps your Chanty environment lean and focused on active work.

Setup guide

Set up Chanty 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 Chanty 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({
    "chanty-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 Chanty 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 Chanty. 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 Chanty 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 Chanty MCP in LangChain

Install the necessary adapters and initialize the MultiServerMCPClient with your endpoint. You then fetch the available tools and pass them directly into your agent constructor to enable Chanty actions.

Yes, the client architecture supports multi-server aggregation. You can combine this MCP Server with your other data sources to create complex, multi-step reasoning chains.

The server remains stateless by default, but you can use the client session to maintain persistent context. This allows your LangGraph agent to remember previous message history.

Since you are using LangChain, you can leverage LangSmith tracing. Every tool interaction provides input and output metrics for debugging your pipeline.

Your data stays within the defined HTTP bounds of your workspace. This server only touches your chat history and user directory, which are secured behind your unique endpoint token.

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