How to Use the Onpipeline MCP in LangChain

Q: Can my agent search companies and contacts at the same time?

Your agent can run parallel queries. It calls listcrmorganizations and listcrmcontacts simultaneously to cross-reference records before updating a pipeline.

Chain raw Onpipeline CRM actions into automated sales runs with your LangChain agents.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Onpipeline MCP to LangChain

Create your Vinkius account to connect Onpipeline 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 Onpipeline with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain multi-step deal creation with LangChain

LangChain agents can map out a sequence of CRM writes without human intervention. By feeding the output of one tool directly into the next, your agent runs `create_crm_organization` to set up the company, then links a new person using `create_crm_contact` in a single run. This chaining prevents data fragmentation across your sales pipeline. Since LangChain tracks every tool input and output in LangSmith, you can audit exactly how your MCP Server parsed a lead email to create the record before it fires `create_crm_deal`.

Audit pipeline activities via LangChain chains

Sales managers need clear visibility into what reps are doing without digging through UI menus. This MCP Server lets your LangChain agent pull recent interactions using `list_activities` and match them against upcoming calendar events via `list_crm_events`. The agent evaluates these combined data streams to flag neglected accounts. You get a direct summary of who needs a call next, built entirely from real-time CRM updates passed through your chain's reasoning steps.

Automate pipeline routing based on deal value

High-value deals require different routing than smaller transactional sales. Your LangChain agent can fetch your current sales setups with `list_pipelines` and inspect specific deal parameters using `get_deal_details` to determine the right path. Based on those details, the agent routes the lead to the correct pipeline stage. You avoid manual sorting errors because the chain handles the conditional logic and executes the move instantly.

Setup guide

Set up Onpipeline 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 Onpipeline 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({
    "onpipeline-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 Onpipeline 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 Onpipeline. 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 Onpipeline 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 Onpipeline MCP in LangChain

You map the output of one step as the input for the next in your chain. For example, the ID returned by `create_crm_contact` feeds straight into the contact field of `create_crm_deal` without writing glue code.

Yes, LangSmith tracks every tool call made by this MCP Server. You can see the precise execution time of calls like `list_crm_deals` right in your tracing dashboard.

The framework handles retries and backoff when tool calls fail. If `list_activities` hits a rate limit, your agent pauses and retries the request automatically.

Your agent can run parallel queries. It calls `list_crm_organizations` and `list_crm_contacts` simultaneously to cross-reference records before updating a pipeline.

Your CRM contacts and deal values never touch third-party servers during transit. This MCP Server runs inside a secure Vinkius V8 sandbox, meaning your API tokens and raw sales data are processed locally and discarded immediately after the tool execution finishes.

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