How to Use the Arcsecond.io MCP in Mastra AI

Q: How do I add Arcsecond.io tools to a Mastra AI agent?

Install the package with npm install @mastra/mcp@latest. Create the connection using new MCPClient({ id: "arcsecond", servers: { name: { url: new URL("...") } } }). Then call mcpClient.listTools() and spread the results into your agent's tool array.

Build resilient astronomical workflows with the Arcsecond.io MCP Server and 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 Arcsecond.io MCP to Mastra AI

Create your Vinkius account to connect Arcsecond.io 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 Arcsecond.io with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Conditional telescope data routing

Wrapping `list_telescopes` in a retry block handles dropped network requests automatically. Mastra AI expects things to break and uses exponential backoff to recover. If the observatory endpoint times out, your workflow pauses and tries again later. You might need to verify a site before pulling its hardware list. Call `list_observing_sites` first. If the site returns active, the workflow branches and fetches the telescopes. If it returns offline, the agent alerts your admin channel.

Automated night log retrieval

The `get_account_check` tool validates your credentials before you run a massive data pull. Checking your connection status is mandatory for reliable workflows. Mastra reads the success state and proceeds to the next step. Once authenticated, your agent hits `list_night_logs`. You configure the workflow to run this sequence every morning at 6 AM. The system grabs the previous night's observation records and dumps them into your database without human oversight.

Deep space object verification

Your workflow can trigger `search_objects` based on a messy user input string to find exact astronomical matches. The agent parses the results and finds the closest target. Research requires precision. Then it passes that exact ID into `get_object` to pull the hard data. This MCP Server integration lets Mastra chain these operations reliably. If the dataset is missing, `list_datasets` fires as a fallback to see what actually exists for that target.

Setup guide

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

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

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

Install the package with `npm install @mastra/mcp@latest`. Create the connection using `new MCPClient({ id: "arcsecond", servers: { name: { url: new URL("...") } } })`. Then call `mcpClient.listTools()` and spread the results into your agent's tool array.

That is exactly what Mastra does best. You configure exponential backoff on the tool call. The workflow engine handles the timing and retry logic automatically.

Vinkius manages the underlying OAuth or API keys for this MCP integration. You just pass your single endpoint token in the HTTP transport headers when initializing the client.

Build a sequential workflow. Step one runs the search and outputs an object ID. Step two takes that ID as a required input variable and fetches the details.

Mastra processes the workflow locally or in your own cloud. The MCP Server runs in an ephemeral zero-trust sandbox. Your night logs and dataset metadata never leak into shared training environments.

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