How to Use the Ayanza MCP in Mastra AI

Q: How do I connect Mastra AI to the Ayanza MCP Server?

Install @mastra/mcp@latest and initialize a new MCPClient pointing to your Vinkius URL. You then fetch the tools with listTools() and spread them into your Mastra Agent configuration.

Q: Can I require approval before Mastra AI deletes an Ayanza task?

Yes, you can configure requireToolApproval on the deletetask tool. This pauses the Mastra workflow and demands human confirmation before any destructive database changes happen.

Q: Does Mastra AI support conditional branching with Ayanza projects?

Absolutely. You can build workflows that check listprojects and branch off into different logic paths depending on whether a specific project exists or needs new tasks.

Q: Is my Ayanza project and team data secure with Mastra?

Every query targeting listusers or getproject runs inside a zero-trust, ephemeral MCP V8 isolate. Your workspace data is processed in transit and never stored on Vinkius servers.

Build resilient, multi-step Ayanza task workflows with Mastra AI and automatic error retries.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Ayanza MCP to Mastra AI

Create your Vinkius account to connect Ayanza 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 Ayanza with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automated task recovery with Mastra AI

This integration uses `update_task` and `create_task` to automatically recover from network failures during Ayanza project updates. When a network hiccup interrupts your flow, Mastra AI uses built-in exponential backoff to retry calls until they succeed. You define these rules directly in your TypeScript workflow. If the agent fails to fetch a project using `get_project`, the workflow handles the failure gracefully without breaking your entire pipeline.

Human-in-the-loop wiki and task moderation

This MCP Server enforces human oversight on destructive operations like `delete_task` before any changes hit your workspace. You probably don't want an autonomous agent deleting tasks or altering documentation without supervision. By setting `requireToolApproval` on critical actions, the agent pauses when it wants to modify a task or query `list_wiki_pages`, waiting for a green light from your team before proceeding.

Workspace discovery via Mastra agents

This MCP Server maps out your entire workspace dynamically by querying `list_users` and `list_tasks` to build a complete directory of team activity. The agent can query team members and cross-reference them with active tasks automatically. You just spread the tools returned from `mcpClient.listTools()` directly into your Mastra Agent definition. The framework handles the transport negotiation automatically, whether it uses standard HTTP or SSE.

Setup guide

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

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

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

Install `@mastra/mcp@latest` and initialize a new `MCPClient` pointing to your Vinkius URL. You then fetch the tools with `listTools()` and spread them into your Mastra Agent configuration.

Yes, you can configure `requireToolApproval` on the `delete_task` tool. This pauses the Mastra workflow and demands human confirmation before any destructive database changes happen.

Absolutely. You can build workflows that check `list_projects` and branch off into different logic paths depending on whether a specific project exists or needs new tasks.

The Mastra client automatically detects the best transport option. It handles both SSE and Streamable HTTP to maintain a stable connection to your tools.

Every query targeting `list_users` or `get_project` runs inside a zero-trust, ephemeral MCP V8 isolate. Your workspace data is processed in transit and never stored on Vinkius servers.

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