How to Use the Mercury MCP in LangChain

Q: Does this handle raw bank statement data?

Yes, liststatements returns the data your agent needs. You can then parse this in your chain to perform automated reconciliation.

Chain your bank data directly into LangChain workflows for automated financial reasoning.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Mercury MCP to LangChain

Create your Vinkius account to connect Mercury 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 Mercury with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain banking operations in LangChain

Feed your financial data into sequential chains where the output of `list_accounts` dictates the next logic step. You can pipe account IDs directly into `get_treasury_balance` to verify liquidity before triggering further operations. This setup allows your agent to handle multi-step tasks without manual intervention. Each tool call links to the next, creating a clear chain of custody for your data.

Observe tool execution with LangSmith

Monitor every interaction between your agent and the Mercury API using standard tracing. When your agent calls `list_transactions`, you see exactly what data entered the chain and what came out. Debugging becomes a matter of checking the trace logs. You don't guess what went wrong; you look at the raw input and output for each function call.

Build multi-server reasoning pipelines

Combine this MCP server with other data sources inside your agent's tool set. Your agent can query a database and cross-reference the results against `list_payments` in a single execution flow. It treats the bank data as just another node in the graph. The agent decides the order of operations based on the data it finds in real-time.

Setup guide

Set up Mercury 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 Mercury 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({
    "mercury-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 Mercury 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 Mercury. 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 Mercury 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 Mercury MCP in LangChain

Use the mcp-adapters package to bridge the connection. Once you instantiate the client, pass the tool list directly into your agent definition.

Yes, provided you manage your environment variables correctly. The client acts as a stateless bridge, passing requests through a secure connection.

It depends on your implementation. By default, the connection is stateless, but you can enable session persistence if your chain requires history.

The agent receives an error response, which you can catch with standard exception handling. You can then instruct the agent to retry or abort.

Yes, `list_statements` returns the data your agent needs. You can then parse this in your chain to perform automated reconciliation.

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

Mastra AI sdk-typescript

Start using the Mercury MCP today

We host it, we monitor it, we maintain it. You just paste one token.

Get started