How to Use the Planet Labs MCP in Mastra AI

Q: Can Mastra AI require approval before downloading Planet Labs assets?

Yes. You can enable requireToolApproval for the getitemassets tool. The workflow pauses, allowing a human to verify the cost and file size before the agent initiates the actual download.

Q: How does Mastra handle failed Planet Labs searches?

Mastra's built-in workflow engine catches errors from quicksearch or getsearchresults. You can configure automatic retries or define a fallback path that alerts your infrastructure team.

Q: Which Planet Labs item types work best with Mastra AI pipelines?

You can query the full catalog using listitemtypes. Most automated workflows rely on PSScene for daily agricultural monitoring or SkySat for high-resolution, targeted change detection.

Build resilient satellite monitoring pipelines with Mastra AI and the Planet Labs MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Planet Labs MCP to Mastra AI

Create your Vinkius account to connect Planet Labs to Mastra AI — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Planet Labs with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Orchestrate continuous imagery feeds

The `create_subscription` tool sets up automated deliveries of new satellite captures to your cloud storage. Mastra AI wraps this MCP operation in a workflow engine that handles network failures. If the Planet API rejects the subscription payload due to rate limits, Mastra automatically retries with exponential backoff until the webhook is successfully registered. You can monitor these automated feeds using `list_subscriptions`. The Mastra agent checks the status of active deliveries on a schedule. If a subscription fails, the workflow branches logically. The agent notifies an admin or attempts to recreate the feed with modified parameters.

Manage recurring MCP Server queries

The `create_saved_search` tool establishes persistent queries for specific geographic areas and cloud cover thresholds. Your Mastra AI workflows can trigger these searches daily without rebuilding the GeoJSON payload from scratch. The agent simply calls `get_search_results` using the saved search ID to pull down the latest PSScene or SkySat captures. To keep the system clean, workflows can audit old queries via `list_saved_searches`. You can build a condition in Mastra that flags searches returning zero images over a 30-day period. This prompts a human-in-the-loop approval to either adjust the cloud cover limits or delete the monitor entirely.

Filter out obscured captures

The `get_cloud_coverage` tool evaluates the exact percentage of clear pixels in a specific image. Mastra AI thrives on this kind of conditional data. You can design a workflow that downloads an image via `get_item_assets` only if the clear area exceeds 90 percent. If the primary image fails the quality check, Mastra branches to an alternative path. The agent executes a new `quick_search` for the previous day or switches from optical imagery to a different sensor type. This guarantees your pipeline always outputs usable data.

Setup guide

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

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

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

Install @mastra/mcp and instantiate a new MCPClient with your Vinkius server URL. Mastra auto-detects the Streamable HTTP transport. Run mcpClient.listTools() and spread them into your agent's tools array.

Yes. You can enable requireToolApproval for the get_item_assets tool. The workflow pauses, allowing a human to verify the cost and file size before the agent initiates the actual download.

Mastra's built-in workflow engine catches errors from quick_search or get_search_results. You can configure automatic retries or define a fallback path that alerts your infrastructure team.

You can query the full catalog using list_item_types. Most automated workflows rely on PSScene for daily agricultural monitoring or SkySat for high-resolution, targeted change detection.

Your geographic boundaries and date filters are processed within a zero-trust V8 sandbox. Once the server returns the imagery metadata or subscription ID, the ephemeral environment is purged. No logs of your requested coordinates are retained on disk.

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