How to Use the CRM PipeRun MCP in LangChain

Q: How do I connect CRM PipeRun to my LangChain agent?

You'll use the langchain-mcp-adapters library. Just instantiate the MultiServerMCPClient with your Vinkius server URL and token, call gettools(), and pass the resulting tool list when you create your agent.

Q: Can a LangChain agent delete activities in CRM PipeRun?

Yes. The deleteactivity tool is included. Your agent can call this tool as part of a chain, but only if you explicitly give it access to that tool when you build the agent.

Q: What's the best way to list open tasks from CRM PipeRun in a LangChain chain?

Use the listactivities tool. It supports filtering, so your agent can ask for specific types of activities or statuses. The structured output is perfect for the next step in your chain to process.

Build multi-step sales bots that manage CRM PipeRun tasks and files with LangChain.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect CRM PipeRun MCP to LangChain

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain CRM Actions Together

This server gives your LangChain agent tools to manage sales activities. You can build chains that first `create_activity` for a new follow-up, then immediately `list_activities` to confirm it's on the schedule for the right person. It's a direct way to make your agent perform sequential, dependent tasks inside your CRM. Because it's LangChain, you see everything. Each tool call—`get_activity`, `update_activity`, whatever—shows up in your trace. You can debug the agent's reasoning step-by-step and see exactly what it decided to do with your PipeRun data, and why. No black boxes.

Automate File Management

Stop manually uploading call notes or contracts. Your agent can now handle it. Give it a file and a destination, and it will use the `upload_file` tool to send it straight to a deal, person, or company record in PipeRun. The base64 encoding is handled for you. Then, build a chain that uses the `get_file` tool to verify the upload succeeded. The output of one tool becomes the input for the next. This lets your agent confirm its own work, creating a reliable, automated workflow for managing CRM files.

Your PipeRun MCP Server

The real power comes from combining tools. This MCP Server gives you the PipeRun connection. But in LangChain, you can give your agent other tools, too. Let it check a calendar API before it calls `create_activity`, or pull customer history from a database before updating a deal. Your agent isn't just a PipeRun bot; it's a sales assistant that coordinates across different systems. The setup is simple: get the tools from the server and pass them to your agent. LangChain handles the rest.

Setup guide

Set up CRM PipeRun 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 CRM PipeRun 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({
    "crm-piperun-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 CRM PipeRun 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 PipeRun. 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 CRM PipeRun 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 CRM PipeRun MCP in LangChain

You'll use the `langchain-mcp-adapters` library. Just instantiate the `MultiServerMCPClient` with your Vinkius server URL and token, call `get_tools()`, and pass the resulting tool list when you create your agent.

Yes. The `delete_activity` tool is included. Your agent can call this tool as part of a chain, but only if you explicitly give it access to that tool when you build the agent.

Use the `list_activities` tool. It supports filtering, so your agent can ask for specific types of activities or statuses. The structured output is perfect for the next step in your chain to process.

Absolutely. That's the point of using LangChain. You can combine the PipeRun tools from this server with any of the 500+ other integrations available, like database connectors or other web APIs.

Your agent will handle data related to activities and files from your PipeRun account. Vinkius secures the connection. Every request from your agent runs in a V8 Isolate sandbox that is destroyed after the call, ensuring your data isn't persisted.

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