How to Use the Cheddar MCP in LangChain

Q: Can a LangChain chain call multiple Cheddar tools in a single run?

Yes. Your agent can run listcheddarplans to find a tier, then immediately trigger addcheddarcharge to apply a fee. The output of the first tool feeds directly into the parameters of the second.

Q: Does this Cheddar integration with LangChain support LangSmith tracing?

Every single call to getcheddarproductinfo or customer tools shows up in your LangSmith dashboard. You see the exact latency, payload sizes, and tool execution status without writing extra logging code.

Run your usage-based billing workflows inside LangChain pipelines using the Cheddar MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Cheddar MCP to LangChain

Create your Vinkius account to connect Cheddar 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 Cheddar with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Direct customer billing lookup in LangChain chains

`get_cheddar_customer_details` fetches raw subscription data and customer files directly into your active chain. Your agent uses this data to decide if a customer is in good standing before running heavy LLM tasks. You don't write custom wrapper code or handle API tokens manually anymore. By pairing this tool with `list_cheddar_customers`, your LangChain pipeline checks account statuses on the fly and pipes the clean JSON payload into your next prompt template.

Automated charge insertion via MCP Server

`add_cheddar_charge` lets your LangChain agent post usage events to Cheddar right after a successful API call or task completion. You track exact consumption and bill for it instantly without waiting for nightly batch jobs. LangSmith tracks the entire execution path, showing you exactly when the tool ran and what charge amount got sent. Combine this with `list_cheddar_plans` to let your agent verify the correct pricing tier before hitting the billing endpoint.

Invoice and transaction auditing

`list_cheddar_invoices` pulls recent billing history directly into your agent's context window. Your agent analyzes payment history to flag accounts with past-due balances before they trigger service cuts. You can chain this with `list_cheddar_transactions` to track down failed payments. The agent handles the lookup, parses the transaction logs, and hands a clean summary to your support team's Slack channel.

Setup guide

Set up Cheddar 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 Cheddar 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({
    "cheddar-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 Cheddar 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 Cheddar. 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 Cheddar 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 Cheddar MCP in LangChain

Install the LangChain MCP adapter package and pass the Vinkius endpoint URL to the client initializer. From there, call the tool getter and pass the list straight to your agent constructor.

Yes. Your agent can run `list_cheddar_plans` to find a tier, then immediately trigger `add_cheddar_charge` to apply a fee. The output of the first tool feeds directly into the parameters of the second.

Every single call to `get_cheddar_product_info` or customer tools shows up in your LangSmith dashboard. You see the exact latency, payload sizes, and tool execution status without writing extra logging code.

Instead of writing and maintaining a custom SDK wrapper for billing APIs, you just expose these tools to your agent. The agent handles the API logic, saving you hours of boilerplate code.

Your billing transactions and customer records stay secure inside the Vinkius V8 sandbox. The server only passes the specific JSON payloads requested by your agent, and no data is stored on Vinkius servers after the session ends.

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