How to Use the Numbers API MCP in LangChain

Q: How do I connect the Numbers API to my LangChain agent?

Install the adapter package and initialize MultiServerMCPClient with the Vinkius endpoint. You then call client.gettools() and pass them directly to your agent constructor. This exposes all five numeric fact tools to your chain instantly.

Q: Can I trace Numbers API tool calls inside LangChain with LangSmith?

Yes, every call to getmathfact or getdatefact is automatically traced when LangSmith is enabled. You will see the precise execution time, payload size, and agent decisions in your debugging console.

Q: How does the agent choose between trivia and math facts?

The LangChain agent inspects the tool schemas for gettriviafact and getmathfact to match the user's intent. If the prompt asks for properties of a prime number, it routes the query to the math tool.

Feed real-time mathematical and historical facts directly into your LangChain reasoning loops.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Numbers API MCP to LangChain

Create your Vinkius account to connect Numbers API 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 Numbers API with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain math and trivia facts in LangChain

`get_math_fact` feeds raw mathematical properties directly into your LangChain sequence, letting your agent evaluate numbers before executing subsequent logical steps. The output of this tool flows directly into your next chain node, turning raw numeric data into structured context. You configure this pipeline using `MultiServerMCPClient` to pull facts on demand. This setup eliminates manual data fetching, giving your agent immediate access to historical dates and mathematical properties during execution.

Track Numbers API MCP Server calls in LangSmith

This MCP Server exposes tools like `get_date_fact` and `get_year_fact` that register directly with your LangChain agent. Every single tool invocation is logged step-by-step in LangSmith, showing you exact latency and token usage for each numeric query. You get full observability into how your ReAct agent decides to pull historical context. If an agent calls `get_year_fact` to verify a date, you see the exact input parameters and JSON payload in your tracing dashboard.

Build multi-step reasoning with random facts

Operating as a wild-card data source inside your LangGraph state machines, `get_random_fact` injects unexpected facts into your agent's reasoning loops. Your agent queries this tool to inject unexpected numeric associations into its decision-making loops. By integrating these five endpoints, your LangChain pipeline handles complex historical queries without hardcoded lookup tables. The agent dynamically routes traffic to `get_trivia_fact` based on the conversation state.

Setup guide

Set up Numbers API 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 Numbers API 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({
    "numbers-api-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 Numbers API 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 Numbers API. 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 Numbers API 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 Numbers API MCP in LangChain

Install the adapter package and initialize `MultiServerMCPClient` with the Vinkius endpoint. You then call `client.get_tools()` and pass them directly to your agent constructor. This exposes all five numeric fact tools to your chain instantly.

Yes, every call to `get_math_fact` or `get_date_fact` is automatically traced when LangSmith is enabled. You will see the precise execution time, payload size, and agent decisions in your debugging console.

Yes, you can combine this server with other data sources using the `MultiServerMCPClient`. Your LangChain agent will dynamically choose between fetching a year fact via `get_year_fact` or querying your database.

The LangChain agent inspects the tool schemas for `get_trivia_fact` and `get_math_fact` to match the user's intent. If the prompt asks for properties of a prime number, it routes the query to the math tool.

This server only processes public numbers, years, and dates, meaning no personally identifiable information is ever sent to the upstream API. Vinkius runs the server in an isolated sandbox, ensuring your internal LangChain configurations and environment variables remain completely private.

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