How to Use the ExchangeRate-API MCP in LangChain

Q: How do I configure ExchangeRate-API with LangChain agents?

Install langchain-mcp-adapters and use MultiServerMCPClient pointing to the Vinkius MCP endpoint. Call client.gettools() and pass them directly to your agent executor.

Q: Can my LangChain agent run multiple ExchangeRate-API tools in one chain?

Yes, your agent can chain listsupportedcurrencies to validate inputs before calling convertcurrencypair. LangChain manages the state across these sequential tool calls automatically.

Q: How do I trace ExchangeRate-API errors in LangChain?

Use LangSmith to trace the inputs and outputs of getlatestrates or any other tool. You will see the exact payload sent to the MCP Server and the API's response directly in your dashboard.

Q: Does this MCP Server support parallel tool calls?

Your LangChain agent can call getlatestrates and gethistoricalrates concurrently if the model supports parallel tool calling. This speeds up comparative financial analysis runs.

Connect ExchangeRate-API directly to your LangChain agents to build multi-step financial pipelines with real-time conversion.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect ExchangeRate-API MCP to LangChain

Create your Vinkius account to connect ExchangeRate-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 ExchangeRate-API with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chained Currency Calculations

`convert_currency_pair` acts as the primary tool for your LangChain agents when executing multi-step financial reasoning. Your agent takes raw pricing data from a database, feeds it to this tool, and passes the output to the next node in your chain without manual intervention. You get full observability into these transactions via LangSmith tracing. Every tool run shows the exact inputs and outputs, so you know why an agent converted USD to EUR before triggering a purchase.

Dynamic Rates in LangChain Chains

`get_latest_rates` pulls live currency exchange data directly into your active LangChain pipelines. Your agent checks this endpoint to evaluate international pricing tiers on the fly before executing downstream steps. By connecting this MCP Server, you bypass writing custom API wrappers for currency lookups in LangChain. The agent decides when to pull rates based on user queries, keeping your financial chains clean and modular.

Historical Auditing with LangChain

`get_historical_rates` lets your LangChain agents analyze past currency fluctuations to audit older transactions. The agent queries specific dates to verify if past invoices matched the actual market rates at the time. You can combine this with `get_enriched_currency_data` to fetch full currency names and flags in the same LangChain execution run. This ensures your final generated reports contain accurate, readable context alongside the raw historical figures.

Setup guide

Set up ExchangeRate-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 ExchangeRate-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({
    "exchangerate-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 ExchangeRate-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 ExchangeRate-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 ExchangeRate-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 ExchangeRate-API MCP in LangChain

Install `langchain-mcp-adapters` and use `MultiServerMCPClient` pointing to the Vinkius MCP endpoint. Call `client.get_tools()` and pass them directly to your agent executor.

Yes, your agent can chain `list_supported_currencies` to validate inputs before calling `convert_currency_pair`. LangChain manages the state across these sequential tool calls automatically.

Use LangSmith to trace the inputs and outputs of `get_latest_rates` or any other tool. You will see the exact payload sent to the MCP Server and the API's response directly in your dashboard.

Your LangChain agent can call `get_latest_rates` and `get_historical_rates` concurrently if the model supports parallel tool calling. This speeds up comparative financial analysis runs.

Your currency rates and conversion queries are processed inside an ephemeral V8 sandbox. Vinkius secures this MCP Server by wiping the session immediately after execution, leaving no persistent logs.

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