How to Use the Relay Workflow Automation MCP in LlamaIndex

Q: Can I query Relay Workflow Automation execution history using LlamaIndex?

Yes. You use listruns to pull execution history, which LlamaIndex indexes into your vector store. This allows your agent to perform semantic search over past runs.

Q: How does LlamaIndex validate inputs before triggering Relay Workflow Automation?

The agent calls getworkflow to retrieve the exact schema requirements for the target pipeline. It compares these requirements against your indexed data to build a valid payload.

Q: Does the Relay Workflow Automation MCP Server support asynchronous execution in LlamaIndex?

Yes. You load the tools asynchronously using totoollistasync() from the McpToolSpec class. This keeps your query pipelines responsive during high-volume operations.

Q: How do I configure this MCP Server within LlamaIndex?

Install llama-index-tools-mcp and initialize the BasicMCPClient. Wrap it in McpToolSpec to register the six workflow tools to your FunctionAgent.

Index and query your Relay Workflow Automation status directly within your LlamaIndex knowledge graphs.

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 LlamaIndex

Create your Vinkius account to connect Relay Workflow Automation to LlamaIndex — 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 LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Index run history into LlamaIndex vector stores

The `list_runs` tool retrieves your recent workflow executions so LlamaIndex can index the results for semantic search. Your RAG agent searches this execution history to answer questions about past workflow performance and failures. By embedding this data, your agent quickly identifies which workflows frequently fail or succeed. You query your vector store to find patterns in execution data without manually digging through API logs.

Query active schemas using the MCP Server

The `list_workflows` tool fetches all available automation blueprints in your account to build a local knowledge index. LlamaIndex uses this index to ground user queries in actual, real-time workflow definitions. When a user asks what automations are available, the agent queries this indexed list instead of guessing. It uses `get_workflow` to pull specific parameters, ensuring the LLM generates accurate inputs based on live schemas.

Execute and track workflows with LlamaIndex agents

The `run_workflow` tool triggers active pipelines using parameters derived directly from your indexed documents. Your LlamaIndex agent extracts variables from a query, matches them against the indexed schema, and starts the run using the MCP protocol. Once triggered, the agent uses `get_run_status` to verify the execution finished successfully. This ensures your knowledge-augmented application only reports completed actions back to the user.

Setup guide

Set up Relay Workflow Automation MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all Relay Workflow Automation MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to Relay Workflow Automation tools.",
)
response = await agent.run("List recent Relay Workflow Automation data")

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 LlamaIndex

Yes. You use `list_runs` to pull execution history, which LlamaIndex indexes into your vector store. This allows your agent to perform semantic search over past runs.

The agent calls `get_workflow` to retrieve the exact schema requirements for the target pipeline. It compares these requirements against your indexed data to build a valid payload.

Yes. You load the tools asynchronously using `to_tool_list_async()` from the `McpToolSpec` class. This keeps your query pipelines responsive during high-volume operations.

Install `llama-index-tools-mcp` and initialize the `BasicMCPClient`. Wrap it in `McpToolSpec` to register the six workflow tools to your `FunctionAgent`.

Your workflow definitions and execution logs are processed in a secure, zero-trust sandbox. We never persist your Relay API credentials or payload values, routing them directly through ephemeral execution channels.

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