How to Use the Pipeliner MCP in LangChain

Q: How do I get my LangChain agent to find all opportunities in a specific Pipeliner pipeline?

You'll build a chain. First, have the agent call listpipelinerpipelines to find the pipeline's ID, then pass that ID as an argument to listpipelineropportunities. LangChain handles passing the output of one tool as the input to the next.

Build custom Pipeliner sales bots with LangChain. Your agent can now run multi-step CRM workflows on its own.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Pipeliner MCP to LangChain

Create your Vinkius account to connect Pipeliner to LangChain — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Pipeliner with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Chain CRM Tools for Complex Queries

Stop babysitting your agent. With LangChain, you build reasoning chains that let your agent decide which Pipeliner tool to use next. It's not about running one command; it's about giving your agent a goal and letting it figure out the steps. For example, your agent can start with `list_pipeliner_pipelines`, pick the right one, then call `list_pipeliner_opportunities` to see the deals inside. If it finds a stalled deal, it can then use `list_pipeliner_activities` to check for recent contact. Each step informs the next one.

Full Observability with this MCP Server

Don't guess what your agent is doing. Every tool call your LangChain agent makes to the Pipeliner server is traced. You see the exact inputs, outputs, latency, and token count for every step in the chain. This means you can debug complex workflows fast. If an agent fails to find a lead with `get_pipeliner_lead`, you'll see the exact ID it used and the API's response. It’s total transparency for your sales automation logic.

Mix Pipeliner Data with Other Sources

Your sales data doesn't live in a vacuum. LangChain's strength is combining different tools in one sequence. Your agent can pull an opportunity from Pipeliner and then query a database or a different API for enrichment. A common pattern is to use `list_pipeliner_opportunities` to find deals closing this quarter, then pass those company names to a web search tool to find recent news. Your agent handles the whole process.

Setup guide

Set up Pipeliner 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 Pipeliner 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({
    "pipeliner-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 Pipeliner 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 Pipeliner. 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 Pipeliner 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 Pipeliner MCP in LangChain

You'll build a chain. First, have the agent call `list_pipeliner_pipelines` to find the pipeline's ID, then pass that ID as an argument to `list_pipeliner_opportunities`. LangChain handles passing the output of one tool as the input to the next.

Yes. When you use this MCP Server with LangChain, every tool call is automatically traced. You can use a service like LangSmith to see a full breakdown of the agent's reasoning and each Pipeliner API call.

LangChain agents can be designed with error handling logic. You can configure your chain to retry a failed call to `get_pipeliner_opportunity`, or to try a different tool if one doesn't return the expected data.

Absolutely. That's a core feature. Your agent can fetch a list of accounts with `list_pipeliner_accounts`, then use a SQL toolkit in the same chain to find matching records in your own database.

Vinkius handles the connection. Your Pipeliner lead, opportunity, and contact data is processed in an ephemeral, zero-trust sandbox for each request. The server doesn't store your CRM data or your credentials after the operation is complete.

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