How to Use the Planet Labs MCP in AutoGen

Q: How do I give my AutoGen agents access to the Planet Labs tools?

First, install the extension: pip install -U "autogen-extmcp". Use the mcpservertools function with your Vinkius server URL to get the list of tool definitions. Then, just pass that list to your AssistantAgent constructor's tools parameter.

Deploy AutoGen agent teams that debate and decide on the best Planet Labs imagery to use for any task.

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 AutoGen

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Build Specialist Imagery Agents

Design a team of agents that collaborate on imagery analysis. You can have a 'Scout' agent that uses `quick_search` to find all available images for an area. It passes the list to a 'QA' agent, which then uses `get_cloud_coverage` to check each one and discard any that are too cloudy. Meanwhile, a 'Finance' agent could use `get_search_statistics` to monitor the number of images being analyzed and warn the team if they risk going over budget. The agents converse and pass data back and forth until they agree on the best images to download.

Negotiate an Imagery Acquisition Strategy

Use a multi-agent conversation to build a robust monitoring plan. One agent, acting as an analyst, might propose using `create_subscription` for a broad area to get daily updates. A second agent, acting as an engineer, could counter by arguing it's more efficient to use `create_saved_search` and only trigger `get_search_results` after a separate weather alert. Through debate, they can settle on a hybrid approach. The final plan is a consensus decision, not a single command, making your system more resilient.

Automate Monitoring with an MCP Server Team

An AutoGen team can manage the entire imagery lifecycle. A 'Scheduler' agent can be configured to trigger a 'Runner' agent every morning. The Runner executes `get_search_results` on a pre-defined saved search and checks for new imagery. If new images are found, it notifies a 'Downloader' agent, which calls `get_item_assets` to get the download URLs and passes them to an external system. This MCP server connects the whole team, with the `McpToolAdapter` handling the tool calls seamlessly.

Setup guide

Set up Planet Labs MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Planet Labs tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Planet Labs_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Planet Labs data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Planet Labs_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Planet Labs data")
    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 AutoGen

First, install the extension: `pip install -U "autogen-ext[mcp]"`. Use the `mcp_server_tools` function with your Vinkius server URL to get the list of tool definitions. Then, just pass that list to your `AssistantAgent` constructor's `tools` parameter.

Yes, that's a perfect use case for AutoGen. You'd give the 'Finder' agent access to `quick_search`, and the 'Approver' agent access to `get_item_assets`. The Finder proposes a list of images, and the Approver makes the final call on which ones to actually download.

It depends on their instructions. You might tell one agent its goal is ad-hoc discovery, so it learns to prefer `quick_search`. You'd tell another its job is to run routine checks, so it learns to use `list_saved_searches` and `get_search_results` instead.

Yes, it does. The adapter fetches the OpenAPI schema from the MCP Server and converts the Planet Labs tool definitions into a format that AutoGen's agents can understand and execute directly. You don't have to do any manual mapping.

Each tool call is an isolated transaction. When one agent calls `quick_search`, the server only sees the search filters for that specific call. It has no access to the broader conversation between your AutoGen agents or any data from other tool calls.

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