How to Use the Flowise MCP in Mastra AI

Q: How do I handle execution failures when calling Flowise from Mastra AI?

You configure Mastra AI to wrap the predict tool in a workflow block with automatic retries. If the Flowise MCP server returns a transient error, the framework automatically backs off and retries the request.

Q: Can I require human approval before Mastra AI triggers a Flowise chatflow?

Yes, you set requireToolApproval to true on the predict tool definition within your Mastra AI agent. This pauses the workflow and waits for an admin signature before executing the low-code backend.

Q: How do I dynamically register Flowise tools inside a Mastra AI agent?

You call listTools() on the MCP client to fetch the tools, then spread them directly into your agent's tool array. This lets your Mastra AI agents automatically discover and execute your Flowise nodes.

Q: How does Mastra AI protect my Flowise credentials and agentflows data?

The listcredentials and listagentflows tools run entirely inside an ephemeral V8 sandbox. Your credentials and visual flow configurations are never stored or inspected, passing directly over encrypted transport to your Mastra runtime.

Run complex, self-healing Flowise workflows using Mastra AI to handle conditional branching and automatic retries.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Flowise MCP to Mastra AI

Create your Vinkius account to connect Flowise to Mastra AI 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 Flowise with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Trigger predictions with automatic retry logic

The `predict` tool executes your low-code backend while Mastra AI wraps the call in its built-in exponential backoff engine. If a third-party API node inside your Flowise chatflow times out, Mastra automatically retries the execution without crashing your application. You spread the tool definitions directly into your agent configuration, letting the framework handle execution failures gracefully. This ensures your production workflows remain stable even during network hiccups.

Inspect Flowise pipelines with Mastra AI and MCP

The `list_tools` tool exposes the exact nodes and integrations configured inside your low-code canvas. Mastra AI reads this list to determine which external services are available, allowing your agent to make routing decisions dynamically. If the system detects a specific email or database tool is missing from the canvas, it branches execution to an alternative notification path. You build complex, multi-step recovery loops that adapt to whatever tools are currently deployed.

Audit and resume complex agentflows

The `list_agentflows` tool retrieves your multi-agent configurations directly from your running instance. Mastra AI uses this directory to coordinate complex handoffs between its own local TypeScript agents and your visual Flowise backends. You can query `get_history` to inspect previous runs before invoking a new step, ensuring your agent has the exact state of the conversation. This prevents duplicate actions and keeps multi-step workflows synchronized.

Setup guide

Set up Flowise MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All Flowise tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "flowise-mcp-client",
  servers: {
    "flowise-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "Flowise Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to Flowise tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent Flowise transactions"
);
console.log(result.text);

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 Flowise. 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 Flowise 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 Flowise MCP in Mastra AI

You configure Mastra AI to wrap the `predict` tool in a workflow block with automatic retries. If the Flowise MCP server returns a transient error, the framework automatically backs off and retries the request.

Yes, you set `requireToolApproval` to true on the `predict` tool definition within your Mastra AI agent. This pauses the workflow and waits for an admin signature before executing the low-code backend.

You call `listTools()` on the MCP client to fetch the tools, then spread them directly into your agent's tool array. This lets your Mastra AI agents automatically discover and execute your Flowise nodes.

The client automatically detects the transport type, establishing either a Streamable HTTP or SSE connection to the Flowise MCP server. This ensures fast, reliable tool execution without manual socket configuration.

The `list_credentials` and `list_agentflows` tools run entirely inside an ephemeral V8 sandbox. Your credentials and visual flow configurations are never stored or inspected, passing directly over encrypted transport to your Mastra runtime.

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