How to Use the Planet Labs MCP in LlamaIndex

Q: How do I add the Planet Labs toolset to my LlamaIndex agent?

Install the package with pip install llama-index-tools-mcp. Then, create a BasicMCPClient with your endpoint URL and pass it to McpToolSpec. Call mcptoolspec.totoollistasync() and give the resulting tools to your FunctionAgent.

Q: Can LlamaIndex use Planet Labs to find and then remember details about specific images?

Absolutely. Your agent can use quicksearch to find images, then call getitemdetails to get their metadata. By letting LlamaIndex index that metadata, the agent 'remembers' it and can answer detailed follow-up questions about those images later.

Q: How can I filter which Planet Labs tools my LlamaIndex agent is allowed to use?

When you create the McpToolSpec, you can pass an allowedtools list containing the names of the only tools you want the agent to access. For example, you could give it 'quicksearch', 'getitemdetails' for a read-only agent.

Build LlamaIndex RAG apps with a knowledge base of live Planet Labs satellite imagery data that you can query.

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 LlamaIndex

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Index Your Satellite Imagery Searches

Turn API responses into a searchable knowledge base. When your agent uses tools like `list_saved_searches` or `get_search_results`, LlamaIndex can automatically index the output. This creates a persistent, queryable record of your activity. Later, you can ask your agent, "What were the cloud cover settings on my Bay Area search?" or "Show me the IDs of the last five subscriptions I created." It will give you an answer grounded in the actual data from past Planet Labs tool calls, not a guess.

Augment Queries with Live API Data

Combine your existing documents with real-time satellite data. When a user asks a question, your LlamaIndex agent can use `quick_search` to get a list of current images for a location. It then calls `get_item_details` on the top results to get specific metadata. This fresh data is injected into the context right alongside your vectorized documents. The final answer is augmented with up-to-the-minute ground truth, which is exactly what RAG is for.

Query Your Planet Labs MCP Server History

By indexing the output of management tools, you create a living history of your operations. An agent can index the data from `list_subscriptions` and `get_search_statistics` over time. This lets you analyze your own usage patterns without having to dig through logs. Ask questions like, "How many images were available over my farm last month?" or "Is my daily wildfire monitoring subscription still active?" Your agent can answer by querying the indexed history from this MCP Server.

Setup guide

Set up Planet Labs MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all Planet Labs MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to Planet Labs tools.",
)
response = await agent.run("List recent Planet Labs data")

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 LlamaIndex

Install the package with `pip install llama-index-tools-mcp`. Then, create a `BasicMCPClient` with your endpoint URL and pass it to `McpToolSpec`. Call `mcp_tool_spec.to_tool_list_async()` and give the resulting tools to your `FunctionAgent`.

Absolutely. Your agent can use `quick_search` to find images, then call `get_item_details` to get their metadata. By letting LlamaIndex index that metadata, the agent 'remembers' it and can answer detailed follow-up questions about those images later.

When you create the `McpToolSpec`, you can pass an `allowed_tools` list containing the names of the only tools you want the agent to access. For example, you could give it `['quick_search', 'get_item_details']` for a read-only agent.

LlamaIndex itself doesn't cache the API calls, but it can index the results. This means the data from a tool call is stored in your configured vector store, so your agent can retrieve it for future queries without having to call the Planet Labs API again.

The server processes imagery metadata, search criteria like GeoJSON boundaries, and account information like saved search lists. Vinkius uses an ephemeral, zero-trust environment for each tool call, and no data from your LlamaIndex agent or Planet Labs account is stored by us.

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