How to Use the INPE (STAC API - Satélites) MCP in LangChain

Q: How does the agent handle large satellite metadata payloads?

The agent receives structured JSON from tools like getcollection or listcollections. You should set system prompts that instruct your agent to extract only the specific properties you need, like cloud cover percentages or acquisition dates, to keep token usage low.

Chain satellite imagery searches directly into your LangChain pipelines using this dedicated MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect INPE (STAC API - Satélites) MCP to LangChain

Create your Vinkius account to connect INPE (STAC API - Satélites) to LangChain 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 INPE (STAC API - Satélites) with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build multi-step satellite search chains

Feed raw coordinates from previous steps straight into `search_items` to find matching CBERS-4 or Amazonia-1 data. Your agent evaluates the return payload, filters by cloud cover, and decides if it needs to query another collection. By linking these tools, you build autonomous loops that pull metadata without manual intervention. The agent uses `list_collections` to discover what is available before narrowing down the search parameters.

Trace MCP Server queries with LangSmith

The `list_collection_items` tool exposes granular imagery metadata that you can easily track using LangSmith tracing. You see the raw JSON inputs and outputs of `get_collection` in your execution timeline to debug spatial queries. This tracing makes it easy to spot why a spatial query failed or where the agent got stuck in a loop. Your agent logs the exact parameters passed to the Brazilian space agency's endpoints so you can monitor rate limits.

Combine spatial metadata with databases

The `get_root_catalog` tool serves as the entry point for your agent to discover and cross-reference satellite swaths with local agricultural databases. Your agent can query `get_conformance` to verify API capabilities before triggering database updates. You can aggregate this server with hundreds of other tools in a single ReAct loop. This setup lets your pipeline run complex spatial decisions without hardcoded logic.

Setup guide

Set up INPE (STAC API - Satélites) 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 INPE (STAC API - Satélites) 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({
    "inpe-stac-api-satelites-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 INPE (STAC API - Satélites) 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 INPE (STAC API). 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 INPE (STAC API - Satélites) 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 INPE (STAC API - Satélites) MCP in LangChain

Install the LangChain MCP adapter package and initialize the client using the Vinkius MCP URL. Once connected, fetch the tools with `client.get_tools()` and pass them directly into your agent constructor to start querying satellite catalogs.

Yes, each tool call is fully visible. LangSmith logs the inputs and outputs of tools like `search_items` or `list_collection_items` so you can debug your spatial search logic in real time.

The server is stateless by default, but you can manage session context on the client side. Use `client.session()` in your LangChain code to keep track of previous collection queries and bounding boxes during a long conversation.

The agent receives structured JSON from tools like `get_collection` or `list_collections`. You should set system prompts that instruct your agent to extract only the specific properties you need, like cloud cover percentages or acquisition dates, to keep token usage low.

Your search parameters, including specific bounding box coordinates and datetime filters, are processed in an isolated V8 sandbox on Vinkius. We do not log or store the coordinates or collection IDs you query from the Brazilian space agency's catalog.

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