How to Use the Pylon MCP in LangChain

Q: Can I trace Pylon tool calls inside LangChain using LangSmith?

Yes, every tool call like getaccount or listissues automatically registers as a span in your LangSmith dashboard. You will see the exact JSON payloads, execution latency, and token costs for every interaction.

Run multi-step support workflows in LangChain by connecting your agents directly to live Pylon customer accounts and issues.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Pylon MCP to LangChain

Create your Vinkius account to connect Pylon 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 Pylon with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Build reactive LangChain chains for Pylon ticket triage

This MCP Server exposes the `list_issues` and `update_issue` tools directly to your LangChain runtimes. Your agents query active support tickets, analyze their content, and apply the correct tags instantly. LangSmith traces every step of this triage chain, showing you exactly why an agent chose a specific tag. You get full visibility into latency and token usage for every single ticket update.

Chain support history lookup with automated replies

The Pylon MCP Server lets your conversational chains pull past conversation threads using `get_issue_messages` before drafting a response. This prevents your agent from repeating questions the customer already answered. Once the context is set, the chain triggers `reply_to_issue` to send the resolution. LangChain coordinates this sequence, feeding the output of the message retrieval step directly into the reply generator.

Connect knowledge bases to other LangChain integrations

Your agent calls `list_knowledge_bases` and `list_articles` to pull documentation directly into your active chain. You can mix these tools with database connections or vector retrievers in a single LangChain run. The model decides when to fetch internal docs and when to query external APIs. This setup turns raw support documents into actionable context for complex, multi-step customer workflows.

Setup guide

Set up Pylon 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 Pylon 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({
    "pylon-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 Pylon 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 Pylon. 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 Pylon 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 Pylon MCP in LangChain

You handle this by adding retry logic or rate-limiting wrappers around your LangChain runnable. The server passes standard rate-limit headers, which your chain can intercept to pause execution before calling `reply_to_issue` again.

Yes, every tool call like `get_account` or `list_issues` automatically registers as a span in your LangSmith dashboard. You will see the exact JSON payloads, execution latency, and token costs for every interaction.

You initialize the client using the LangChain MCP adapter and call the get tools method to get the tool array. Pass this array directly to your agent constructor so it can choose when to run `create_issue` or `update_issue`.

Yes, LangChain allows multi-server aggregation. You can combine this server with other endpoints, giving your agent the ability to query CRM data in one step and update Pylon issues in the next.

Your support tickets and account details remain in Pylon and are only accessed during live tool execution. Vinkius runs the server in an isolated, zero-trust sandbox, meaning no support data or knowledge base articles are ever stored or cached on our end.

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