How to Use the ArcXP MCP in Mastra AI

Q: Can I require human approval before my agent deletes ArcXP content?

Yes. Mastra supports a requireToolApproval option. You can apply this to the deleteanscontent tool, which will pause the workflow and wait for a person to confirm before the destructive action proceeds.

Q: What does a Mastra AI workflow for updating an ArcXP article with a new photo look like?

It's a two-step sequence. First, your agent uses the searchphotoassets tool to find the right image. Then, it passes the image data to a second step that uses the updateanscontent tool to revise the article.

Build ArcXP publishing workflows that handle errors, retries, and complex logic automatically with Mastra AI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect ArcXP MCP to Mastra AI

Create your Vinkius account to connect ArcXP 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 ArcXP with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate Your Publishing Pipeline

Chain ArcXP operations together into a single, reliable workflow. A Mastra agent can `search_ans_content` to find a draft, pass it to `update_ans_content` for revisions, and then notify a Slack channel when it's done. This isn't a simple script. Mastra manages the state between each step, ensuring that the output of one tool correctly feeds into the next. You define the sequence, and the agent executes it.

Build Resilient Content Syncs

Network connections fail. APIs return errors. Mastra is built for this. If a call to `create_ans_content` fails, you don't have to write your own retry logic. Mastra's engine can do it for you, with exponential backoff included. Your workflow can also branch based on failure. If an update fails after three tries, the agent can be instructed to create a ticket or alert an administrator. This makes your automation far more robust.

Design Complex Workflows with this MCP Server

Real-world publishing isn't always a straight line. With Mastra, your agent can make decisions. For example, it could try to `get_video_asset` for an article. If that returns nothing, it can branch and use `search_photo_assets` to find a fallback image instead. This conditional logic is native to Mastra's workflow engine. It lets you build sophisticated processes that handle different content scenarios before finally calling `update_ans_content` to publish the result. It's a smarter way to automate.

Setup guide

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

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

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

Mastra's workflow engine has built-in retry capabilities. If your agent's call to the `create_ans_content` tool fails, the engine can automatically try again after a delay. You configure the number of retries, not the code.

Yes. Mastra supports a `requireToolApproval` option. You can apply this to the `delete_ans_content` tool, which will pause the workflow and wait for a person to confirm before the destructive action proceeds.

It's a two-step sequence. First, your agent uses the `search_photo_assets` tool to find the right image. Then, it passes the image data to a second step that uses the `update_ans_content` tool to revise the article.

In your Mastra client configuration, you define separate MCP server connections, each with its own URL. Your workflow can then select the appropriate connection, allowing your agent to target the right ArcXP environment.

Your Mastra workflows only interact with the ArcXP data you target, like ANS content objects, author profiles, or media library assets. The connection is managed by Vinkius, and every operation runs in a sandboxed, ephemeral environment. This isolates your credentials and workflow state.

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