How to Use the FlowUs MCP in Mastra AI

Q: How do I register FlowUs tools in a Mastra AI agent?

Initialize the client using new MCPClient and point it to the Vinkius endpoint. Call mcpClient.listTools() and spread those tools directly into your agent's tool array so it can run actions like listblocks.

Q: Can I require human approval before Mastra AI modifies a FlowUs database?

Yes, you can set requireToolApproval on the tool level. This forces the workflow to halt before executing createdatabaserow, giving you a chance to review the entry.

Q: How does Mastra AI handle FlowUs API rate limiting?

The workflow engine has built-in retry logic. If a getdatabase call hits a rate limit, the client backs off and retries automatically without failing the entire run.

Q: Does this MCP integration support multi-step workspace migrations?

Absolutely. You can chain tools like listpages and updatepage inside a Mastra workflow to automate complex document updates across your entire workspace using this MCP Server.

Build resilient Mastra AI workflows that write, update, and manage FlowUs databases with automatic retries and approvals.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect FlowUs MCP to Mastra AI

Create your Vinkius account to connect FlowUs 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 FlowUs with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build Resilient Database Workflows in Mastra AI

Automated data entry is fragile, but Mastra AI makes it bulletproof. When your agent attempts to write a new record using `create_database_row`, the workflow engine automatically handles rate limits and API hiccups with built-in exponential backoff. If a query fails midway, the system doesn't crash. It retries `query_database` or falls back to a different branch, ensuring your workspace records remain accurate and complete.

Human-Approved Page Updates with this MCP Server

Letting an agent modify documentation without supervision is a recipe for chaos. By configuring `requireToolApproval` in your Mastra setup, every `update_page` action pauses until a human clicks approve. The agent drafts the changes, reads the existing structure with `get_page`, and queues the edit. You keep total control over your wiki pages while letting the agent do the heavy drafting.

Automated Hierarchy Generation and Workspace Sync

Managing large documentation structures requires strict organization. Your Mastra agents can map out entire workspaces by calling `list_databases` and `list_pages` to build conditional execution paths. If a required page is missing, the agent branches to call `create_page` before writing any content. This ensures your knowledge base stays organized without manual human intervention.

Setup guide

Set up FlowUs 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 FlowUs 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: "flowus-mcp-client",
  servers: {
    "flowus-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

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

const result = await agent.generate(
  "List recent FlowUs 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 FlowUs. 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 FlowUs 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 FlowUs MCP in Mastra AI

Initialize the client using `new MCPClient` and point it to the Vinkius endpoint. Call `mcpClient.listTools()` and spread those tools directly into your agent's tool array so it can run actions like `list_blocks`.

Yes, you can set `requireToolApproval` on the tool level. This forces the workflow to halt before executing `create_database_row`, giving you a chance to review the entry.

The workflow engine has built-in retry logic. If a `get_database` call hits a rate limit, the client backs off and retries automatically without failing the entire run.

Absolutely. You can chain tools like `list_pages` and `update_page` inside a Mastra workflow to automate complex document updates across your entire workspace using this MCP Server.

Yes, your workspace user accounts, page blocks, and database rows are protected. Your API tokens are stored securely in the Vinkius zero-trust vault, never exposed to your Mastra AI runtime. The MCP Server only handles the execution of tools like `list_users` or database queries, keeping your workspace configuration safe.

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