How to Use the Pipeline CRM MCP in LangChain

Q: How do I pass Pipeline CRM tools to a LangChain agent?

Install langchain-mcp-adapters and initialize the client with your Vinkius endpoint. Call client.gettools() to retrieve tools like listpipelinedeals and pass them directly into your createagent call.

Q: Is the LangChain integration stateless by default?

Yes, the connection runs stateless unless you use client.session() to keep context active. This keeps your memory clean and prevents token bloat when running quick checks on listpipelinecompanies.

Build LangChain chains that query Pipeline CRM data directly to feed your multi-step sales agents.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Pipeline CRM MCP to LangChain

Create your Vinkius account to connect Pipeline CRM 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 Pipeline CRM with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Build multi-step LangChain MCP Server loops

The Pipeline CRM MCP Server lets your LangChain agents run multi-step sales tasks by combining tools like `list_pipeline_deals` and `list_pipeline_tasks`. The agent looks at your active pipeline, catches lagging deals, and schedules the next action without you writing glue code. LangSmith monitors the whole sequence. You see every tool call, token cost, and raw payload as your chain hops from checking a deal to looking up the associated contact details.

Chain contact lookups with context

This integration maps Pipeline CRM contacts to your LangChain agent memory using `get_pipeline_person` and `list_pipeline_notes`. Your agent pulls the exact history of a lead before drafting an email, ensuring it knows every past interaction. Because LangChain handles state through custom runnables, you can feed these notes straight into your prompt templates. The agent gets a clean, structured view of the customer's history instead of guessing.

Coordinate team schedules automatically

Your LangChain chain coordinates team schedules by combining `list_pipeline_events` with `list_pipeline_users` to see who is free and who is assigned to a deal. The agent matches open calendar slots with available sales reps to book follow-ups. You do not need to hardcode routing logic. The ReAct agent decides which team member gets the task based on the real-time user list it pulls from the server.

Setup guide

Set up Pipeline CRM 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 Pipeline CRM 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({
    "pipeline-crm-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 Pipeline CRM 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 Pipeline CRM. 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 Pipeline CRM 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 Pipeline CRM MCP in LangChain

Install `langchain-mcp-adapters` and initialize the client with your Vinkius endpoint. Call `client.get_tools()` to retrieve tools like `list_pipeline_deals` and pass them directly into your `create_agent` call.

Yes, you can mix these CRM tools with any of LangChain's 500+ integrations in a single chain. Your agent can pull a deal using `get_pipeline_deal` and immediately query an external database to check inventory.

LangSmith traces the exact inputs and outputs of tools like `list_pipeline_tasks` in real time. You can inspect latency and token counts for every single API call your agent makes.

Yes, the connection runs stateless unless you use `client.session()` to keep context active. This keeps your memory clean and prevents token bloat when running quick checks on `list_pipeline_companies`.

Your deal values, contact notes, and task lists never leave the Vinkius sandbox during execution. Vinkius runs the server in an isolated container, passing only the final outputs back to your application.

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