How to Use the Relay Workflow Automation MCP in LangChain

Q: How do I pass variables to Relay Workflow Automation using LangChain?

You use the runworkflow tool by passing a formatted JSON object matching the workflow's input schema. Your LangChain agent handles this structure automatically during chain execution.

Q: Can LangChain handle long-running Relay Workflow Automation executions?

Yes. Your agent uses getrunstatus to poll the execution state at defined intervals. If the run stalls, the agent can trigger cancelrun to clean up resources.

Q: What is the setup process for this MCP Server?

Install langchain-mcp-adapters and connect using MultiServerMCPClient. Retrieve the tools with client.gettools() and pass them directly to your agent constructor.

Run and monitor Relay Workflow Automation runs natively within your LangChain execution chains.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Relay Workflow Automation MCP to LangChain

Create your Vinkius account to connect Relay Workflow Automation 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 Relay Workflow Automation with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Chain Relay executions directly with LangChain agents

The `run_workflow` tool triggers a specific execution with custom JSON inputs right inside your LangChain runnable sequence using our MCP connection. Your agent reads upstream variables, constructs the required JSON payload, and executes the target workflow without manual intervention. LangSmith tracks the exact inputs passed to `run_workflow` and records the resulting run ID. This lets you debug execution payload mismatches and track latency across your entire multi-step agentic chain.

Discover active pipelines using the MCP Server

The `list_workflows` tool pulls all active automations from your Relay account to let your agent discover available tasks dynamically. Your LangChain agent calls this tool first to map available endpoints before attempting to trigger any specific run. After discovery, the agent uses `get_workflow` to inspect the exact parameters a specific pipeline expects. This double-check step prevents execution failures by validating schemas before passing variables to the execution engine.

Track and cancel runs inside LangChain loops

The `get_run_status` tool queries the live execution state of your triggered Relay workflows. When a run takes too long or hits an error, your LangChain loop detects the stalled state and decides whether to wait or pivot. If a run hangs or fails validation mid-flight, the agent invokes `cancel_run` to stop the active execution. This prevents runaway API usage and keeps your LangChain execution pipelines clean and predictable.

Setup guide

Set up Relay Workflow Automation 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 Relay Workflow Automation 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({
    "relay-workflow-automation-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 Relay Workflow Automation 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 Relay. 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 Relay Workflow Automation 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 Relay Workflow Automation MCP in LangChain

You use the `run_workflow` tool by passing a formatted JSON object matching the workflow's input schema. Your LangChain agent handles this structure automatically during chain execution.

Yes. Your agent uses `get_run_status` to poll the execution state at defined intervals. If the run stalls, the agent can trigger `cancel_run` to clean up resources.

Every tool call is recorded as a distinct step in your LangChain execution trace. You see the exact payload inputs, execution latency, and output states directly in your LangSmith dashboard.

Install `langchain-mcp-adapters` and connect using `MultiServerMCPClient`. Retrieve the tools with `client.get_tools()` and pass them directly to your agent constructor.

The server processes your workflow configurations and input variables inside an ephemeral V8 sandbox. No payload data is stored or cached on our servers, and all traffic travels over encrypted connections directly to the Relay API.

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