How to Use the Planet Labs MCP in LangChain

Q: How do I set up the Planet Labs tools with LangChain?

First, pip install langchain-mcp-adapters. Then, instantiate the MultiServerMCPClient with your Vinkius endpoint URL. Call the client.gettools() method and pass the resulting list directly to your agent executor.

Q: Can my LangChain agent create a recurring Planet Labs search for new imagery?

Yes. The agent should use the createsavedsearch tool to define the area and filters. It can then use the returned ID to periodically call getsearchresults to find new images that match the criteria.

Build LangChain agents that chain Planet Labs API calls for automated satellite imagery analysis and delivery.

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 LangChain

Create your Vinkius account to connect Planet Labs to LangChain — 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Chain Imagery Search and Delivery

Build agents that execute multi-step imagery workflows. Your agent can first call `create_saved_search` to define a monitoring area, like a farm or coastline. The tool returns a search ID, which is then passed as input to `get_search_results` in the next step of the chain to fetch the latest matching images. From there, the chain continues. If the results look good, your agent can take the original search parameters and call `create_subscription` to get new imagery delivered automatically. It’s a complete, observable sequence from ad-hoc search to automated delivery, with LangSmith tracing every step.

Add Ground Truth to Your Agents

Give your agents the ability to reason about image quality before taking action. Inside a ReAct loop, an agent can use `quick_search` to get a list of candidate images, then iterate through them, calling `get_item_details` and `get_cloud_coverage` for each one. Based on that data, the agent can decide which images are clear enough to use. For the keepers, it calls `get_item_assets` to get the final download URLs. This avoids wasting time and money downloading cloudy or irrelevant scenes.

Manage Your Planet Labs MCP Server

Your LangChain agent can manage its own monitoring configuration. Before creating a new search, it can call `list_saved_searches` to see if a similar one already exists. This prevents duplicate work and keeps your Planet Labs account clean. Same goes for data delivery. The agent can check the output of `list_subscriptions` to review active deliveries before adding a new one. This MCP Server handles the Planet Labs authentication, so your agent just focuses on the workflow logic.

Setup guide

Set up Planet Labs MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Planet Labs tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "planet-labs-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Planet Labs transactions"
    })
    print(result["messages"][-1].content)

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 LangChain

First, `pip install langchain-mcp-adapters`. Then, instantiate the `MultiServerMCPClient` with your Vinkius endpoint URL. Call the `client.get_tools()` method and pass the resulting list directly to your agent executor.

Yes. The agent should use the `create_saved_search` tool to define the area and filters. It can then use the returned ID to periodically call `get_search_results` to find new images that match the criteria.

Your agent should be designed to loop. After the first call to `get_search_results`, it checks if the response contains more results and then calls the tool again with the next page number until all images have been retrieved.

Every tool call made by your LangChain agent through this MCP Server is automatically traced. In a platform like LangSmith, you can see the exact inputs, outputs, latency, and token usage for each call to tools like `quick_search` or `create_subscription`.

Yes. The connection is secured, and the server itself is ephemeral. It only processes the data needed for a single tool call—like GeoJSON coordinates for a search or filter criteria for a subscription—and does not store it after the operation is complete.

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