How to Use the Finch MCP in LangChain

Q: Can I trace Finch payroll queries using LangChain and LangSmith?

Yes, every call to tools like listpaystatements or getcompany shows up in your LangSmith dashboard. You can inspect the exact payload, latency, and token cost of each HRIS query.

Q: How does LangChain handle connection failures with Finch?

The MultiServerMCPClient manages the underlying connection. If a call to introspect or getme fails, LangChain throws a standard execution error that you can catch and retry within your chain logic.

Q: Can my LangChain agent run multiple Finch tools in parallel?

Yes, you can run multiple lookup tools like getindividual and getemployment concurrently using standard async execution in your chain. This speeds up data gathering across large employee directories.

Fetch raw payroll and HR data 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 Finch MCP to LangChain

Create your Vinkius account to connect Finch 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 Finch with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Map Employee Directories in LangChain Runs

LangChain agents can map out entire organizational structures by chaining a call to `list_directory` directly into individual profile lookups. Instead of hardcoding API requests, you feed the directory output straight into `get_individual` to pull specific details like SSNs or emails on demand. This multi-step execution shines when you use LangSmith to trace the exact token usage and latency of each HRIS step. Your agent decides which worker needs checking, gets their unique ID, and executes the lookup without manual routing.

Audit Payroll Records with LangChain Chains

You can construct a chain that pulls pay groups via `list_pay_groups` and immediately feeds those IDs into `list_pay_statements`. The agent inspects the resulting payroll data to spot discrepancies in tax withholding or gross pay. Because LangChain supports over 500 integrations, you can instantly pipe these parsed pay statements into a SQL database or an external ledger. The entire process runs through a single MCP Server connection, meaning no complex authentication setup for your agent.

Check Sync Jobs Using this MCP Server

Keep tabs on massive data syncs by letting your LangChain agent run `list_automated_jobs` and inspect specific runs with `get_automated_job`. If a sync fails, the agent reads the error payload and decides whether to retry or alert your team. By wrapping this MCP Server in a stateless `MultiServerMCPClient`, you can combine payroll monitoring with system status checks in one unified pipeline. LangChain handles the tool declarations, letting you focus on the logic.

Setup guide

Set up Finch 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 Finch 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({
    "finch-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 Finch 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 Finch. 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 Finch 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 Finch MCP in LangChain

You use LangChain's chaining syntax or a ReAct agent to feed the output of `list_directory` straight into `get_employment`. The agent handles the parameter mapping automatically based on the schemas exposed by the MCP Server.

Yes, every call to tools like `list_pay_statements` or `get_company` shows up in your LangSmith dashboard. You can inspect the exact payload, latency, and token cost of each HRIS query.

The `MultiServerMCPClient` manages the underlying connection. If a call to `introspect` or `get_me` fails, LangChain throws a standard execution error that you can catch and retry within your chain logic.

Yes, you can run multiple lookup tools like `get_individual` and `get_employment` concurrently using standard async execution in your chain. This speeds up data gathering across large employee directories.

Your SSNs, salary figures, and tax details never touch third-party servers. Vinkius isolates the Finch MCP Server in a zero-trust V8 sandbox, passing the raw data directly to your local LangChain runtime over an encrypted channel.

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