How to Use the Aidbase MCP in Mastra AI

Q: Can I add a human approval step to my Aidbase workflows in Mastra AI?

Yes. Mastra AI supports requireToolApproval in its agent configuration. You can design a workflow where an agent drafts a reply using Aidbase tools, then pauses and waits for a person to approve the action before it sends the message.

Q: What's the setup for connecting Aidbase to a Mastra AI agent?

Install the package with npm install @mastra/mcp@latest. In your code, create a new MCPClient and point it to your Vinkius URL. Your Mastra AI agent can then access all the Aidbase tools returned by mcpClient.listTools().

Build resilient customer support workflows for Aidbase with Mastra AI's automated retries and conditional logic.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Aidbase MCP to Mastra AI

Create your Vinkius account to connect Aidbase 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 Aidbase with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate Knowledge Base Syncing

This server provides tools to add content to your Aidbase knowledge bases, like `add_aidbase_website_knowledge`. You can build a Mastra AI agent that reads a list of URLs and adds each one to Aidbase. Where Mastra AI shines is in reliability. If the `add_aidbase_website_knowledge` call fails for one URL due to a temporary network blip, the agent's built-in retry logic will try again automatically. You can also add a conditional step to log any URLs that permanently fail to a separate system for manual review.

Create Self-Healing Support Agents

Your agent can use the `check_aidbase_status` tool to make sure the service is online before acting. This allows you to build much more robust automation that doesn't break when a dependency has a problem. A Mastra AI workflow can periodically check the status. If the API is down, the workflow pauses, waits using exponential backoff, and only resumes its tasks—like sending replies with `send_aidbase_reply`—once the Aidbase API is healthy again. No human intervention needed.

Build Complex Ticket Triage Workflows

Combine multiple Aidbase tools into a single, reliable workflow. For example, an agent can use `list_aidbase_inboxes` to find new messages, `get_aidbase_inbox` to read their content, and then use `list_aidbase_knowledge` to find a relevant article. Mastra AI's workflow engine ensures this multi-step process completes. If a step fails, it can be retried. You can add conditional logic, like 'if the message contains 'urgent', then use `send_aidbase_reply` to send an immediate confirmation and notify a human'.

Setup guide

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

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

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

Mastra AI has built-in automated retries with exponential backoff. If a call to an Aidbase tool fails from a transient error, your agent automatically tries again. This prevents your entire workflow from failing.

Yes. Mastra AI supports `requireToolApproval` in its agent configuration. You can design a workflow where an agent drafts a reply using Aidbase tools, then pauses and waits for a person to approve the action before it sends the message.

Install the package with `npm install @mastra/mcp@latest`. In your code, create a `new MCPClient` and point it to your Vinkius URL. Your Mastra AI agent can then access all the Aidbase tools returned by `mcpClient.listTools()`.

You use Mastra AI's workflow logic. Your agent can try to call `add_aidbase_website_knowledge` inside a try/catch block. If it fails, your `catch` logic can trigger a different action, like logging the failed URL to a database for someone to look at later.

Yes. The MCP server only accesses the specific Aidbase chatbot details, inbox messages, or knowledge items required for the tool you call. Every operation runs in a completely isolated Vinkius sandbox that is wiped clean after the request is finished.

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