How to Use the Merge (Unified Integration API) MCP in LangChain

Q: Can I trace Merge (Unified Integration API) tool latency inside LangChain?

Yes, every call to tools like listtickets or listaccounts registers as a tool run in LangSmith. You get exact millisecond breakdowns of how long the underlying API takes to respond.

Q: How does this MCP Server handle multiple CRM integrations in LangChain?

The server uses the listaccounts tool to distinguish between different customer accounts across your CRM integrations. Your LangChain agent reads the account details to route queries to the correct tenant.

Get unified HRIS, ATS, and CRM data directly inside 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 Merge (Unified Integration API) MCP to LangChain

Create your Vinkius account to connect Merge (Unified Integration 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 Merge (Unified Integration API) with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain HRIS and ATS data queries sequentially

The `list_employees` tool pulls active team directories from your linked HRIS platforms directly into your LangChain runnables. Your agent can inspect this list, identify a hiring manager, and immediately pass their ID to `list_candidates` to map active job applications. This sequential chaining lets you build multi-step workflows without writing custom glue code for every different HRIS provider. You get raw JSON payloads that feed straight into the next link of your chain.

Trace unified CRM and support ticket data in LangSmith

The `list_contacts` and `list_tickets` tools expose customer interactions and support histories to your LangChain agent. When an agent queries these endpoints to resolve an account issue, every tool execution is tracked inside LangSmith. You see the exact latency, token count, and raw payloads returned by the MCP Server. This visibility means you can debug failing CRM queries or slow ticket fetches instantly.

Resolve integration boundaries with this MCP Server

The `get_account_details` tool checks the status and limits of your active customer integrations. Your LangChain agent runs this check before executing heavy queries like `list_companies` or `list_accounts` to prevent API rate limits from breaking the chain. If an integration is paused or reaches its limit, the agent catches the boundary details and routes the chain to an alternative path. You handle multi-tenant API failures gracefully without manual intervention.

Setup guide

Set up Merge (Unified Integration 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 Merge (Unified Integration 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({
    "merge-unified-integration-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 Merge (Unified Integration 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 Merge. 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 Merge (Unified Integration 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 Merge (Unified Integration API) MCP in LangChain

You configure your LangChain agent to inspect the response metadata returned by `list_employees` or `list_candidates`. If a next-page token exists, the agent passes it to the subsequent tool call in the loop. This keeps your memory footprint low during large data fetches.

Yes, every call to tools like `list_tickets` or `list_accounts` registers as a tool run in LangSmith. You get exact millisecond breakdowns of how long the underlying API takes to respond.

The server uses the `list_accounts` tool to distinguish between different customer accounts across your CRM integrations. Your LangChain agent reads the account details to route queries to the correct tenant.

Import the adapter, initialize the server client, and call the get tools method. You pass the resulting list directly to your agent's tool binder, exposing all eight endpoints immediately.

Your employee records and candidate resumes pass through ephemeral memory inside a zero-trust V8 sandbox. No data is stored on disk, and the endpoint token handles authentication without exposing raw API keys to the client.

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