How to Use the BigOven MCP in LangChain

Q: Can a LangChain chain use BigOven to filter by specific ingredients?

Yes, the model uses searchbyingredient to find matches based on a list of items. It then passes those results to subsequent steps in your pipeline to build complete meal plans.

Build multi-step LangChain recipe pipelines that search ingredients, fetch instructions, and analyze reviews in a single run.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect BigOven MCP to LangChain

Create your Vinkius account to connect BigOven 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 BigOven with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate recipe discovery in LangChain pipelines

This MCP Server exposes tools to search and fetch raw culinary data directly inside your agent runs. Your LLM can call `search_recipes` to find dishes, then feed those IDs straight into `get_recipe` to parse ingredients. It turns a manual search process into a single, predictable chain. You track every single API transition inside LangSmith to debug latency or token usage. If a user asks for a meal plan, the agent coordinates these tool calls sequentially, passing output to input without you writing custom glue code.

Targeted ingredient filtering with LangChain

`search_by_ingredient` lets your pipeline hunt for dishes based on what is left in the fridge. The agent checks your database, finds the available items, and queries the API to return matching recipes. No more guessing what to cook with leftover chicken. You can chain this with `get_recipe_reviews` to filter out poorly rated dishes before showing them to the user. The entire flow runs inside a secure V8 sandbox, meaning your API tokens stay hidden from the client-side code.

Curated menu generation via MCP tools

`list_collections` retrieves seasonal and curated lists of dishes to inspire your users. Your agent reads these collections, then uses `get_collection` to extract the exact recipes. It works well for generating weekly meal plans that adapt to current trends. The model can check `list_categories` first to make sure it only pulls vegetarian or gluten-free options. Because it is a standard MCP setup, you connect this server to your existing chains with about five lines of Python.

Setup guide

Set up BigOven 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 BigOven 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({
    "bigoven-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 BigOven 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 BigOven. 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 BigOven 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 BigOven MCP in LangChain

Install the adapter and register the server URL. Your agent gets access to tools like `get_recipe` instantly, letting the LLM decide when to call them during a conversation.

Yes, the model uses `search_by_ingredient` to find matches based on a list of items. It then passes those results to subsequent steps in your pipeline to build complete meal plans.

Every tool execution, from searching titles to fetching reviews, gets logged in LangSmith. You can see the exact inputs, outputs, and latency for every API call.

Vinkius handles the underlying API credentials on its secure gateway. You only need to pass your single Vinkius endpoint token when initializing the client in your code.

Your search queries and API keys run inside isolated, ephemeral V8 containers. No search history or culinary preferences are stored on the host after the session closes.

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