How to Use the Planet Labs MCP in Pydantic AI

Q: How does Pydantic AI validate Planet Labs search parameters?

The framework runs incoming arguments for quicksearch through its internal validation loop. This ensures your Pydantic AI agent only sends correctly formatted GeoJSON and ISO 8601 dates to the Planet Labs API.

Q: Can I handle automated imagery subscriptions safely using Pydantic AI and Planet Labs MCP?

Yes, your Pydantic AI agent calls createsubscription and validates the returned Planet Labs subscription ID and status. Pydantic AI guarantees the delivery destination structure matches your schema before activating the Planet Labs feed.

Q: What tool does a Pydantic AI agent use on this MCP Server to check Planet Labs image quality?

The Pydantic AI agent executes getcloudcoverage to fetch clear and cloudy percentages for a specific Planet Labs item. The returned floats are validated against your Pydantic AI models to ensure they fall within the expected range.

Q: How do I discover supported Planet Labs satellite constellations in Pydantic AI?

Run listitemtypes within your Pydantic AI agent loop to get a typed list of Planet Labs constellations like PSScene and SkySat. Pydantic AI parses this list, making it easy to select resolutions programmatically.

Run type-safe Planet Labs satellite imagery searches with runtime validation using Pydantic AI.

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 Pydantic AI

Create your Vinkius account to connect Planet Labs to Pydantic 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 Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Validate satellite metadata at runtime with Pydantic AI

Your Pydantic AI agent runs `get_item_details` to fetch Planet Labs imagery metadata and instantly validates the schema against your strict Python models. This validation prevents silent data corruption from unexpected Planet Labs API payload changes within your Pydantic AI pipeline. The Pydantic AI agent executes `quick_search` to find Planet Labs PSScene and SkySat imagery. It's the safest way to ensure the returned Planet Labs coordinates, cloud cover percentages, and acquisition times strictly conform to your Pydantic AI types.

Run type-safe monitoring via this MCP Server

This MCP Server enables your Pydantic AI agent to call `create_saved_search` to establish verified Planet Labs monitoring parameters. The Pydantic AI agent validates the returned Planet Labs search ID before storing it in your local database. Your Pydantic AI agent executes `get_search_results` to pull the latest Planet Labs imagery. It's a direct step that parses the paginated Planet Labs results through Pydantic validators to guarantee your downstream GIS applications only receive clean, typed data.

Verify asset types and download paths securely

Your Pydantic AI agent connects to this MCP Server to call `get_item_assets` to retrieve direct download URLs and file sizes for Planet Labs items. The Pydantic AI framework validates these Planet Labs asset objects at runtime to ensure download links are well-formed URLs so there's no guesswork. Your Pydantic AI agent uses `list_asset_types` to map out the properties of Planet Labs visual, analytic, and UDM assets. The Pydantic AI agent checks these properties against your workflow requirements before initiating any Planet Labs network requests.

Setup guide

Set up Planet Labs MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "planet-labs-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Planet Labs tools.",
)

result = await agent.run("List recent Planet Labs transactions")
print(result.output)

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 Pydantic AI

The framework runs incoming arguments for `quick_search` through its internal validation loop. This ensures your Pydantic AI agent only sends correctly formatted GeoJSON and ISO 8601 dates to the Planet Labs API.

Yes, your Pydantic AI agent calls `create_subscription` and validates the returned Planet Labs subscription ID and status. Pydantic AI guarantees the delivery destination structure matches your schema before activating the Planet Labs feed.

The Pydantic AI agent executes `get_cloud_coverage` to fetch clear and cloudy percentages for a specific Planet Labs item. The returned floats are validated against your Pydantic AI models to ensure they fall within the expected range.

Run `list_item_types` within your Pydantic AI agent loop to get a typed list of Planet Labs constellations like PSScene and SkySat. Pydantic AI parses this list, making it easy to select resolutions programmatically.

Your Planet Labs credentials reside in Vinkius's zero-trust environment, separate from your local Pydantic AI runtime. Pydantic AI only handles the strongly-typed inputs and outputs of the MCP Server, keeping your credentials hidden.

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