How to Use the Planet Labs MCP in CrewAI

Q: How do I restrict a CrewAI agent from creating Planet Labs MCP subscriptions?

Use the toolfilter configuration to expose only read-only tools like getitemdetails or listitemtypes. Keep createsubscription assigned strictly to an authorized manager agent.

Q: What happens if a Planet Labs search returns too many results?

The getsearchresults tool supports pagination. A CrewAI agent can be instructed to read the first page of results, evaluate the quality, and decide autonomously whether to request the next page or refine the search criteria.

Deploy autonomous GIS teams using CrewAI and the Planet Labs MCP Server to monitor global change.

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 CrewAI

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Coordinate complex imagery searches

The `quick_search` tool accepts complex GeoJSON boundaries and precise date ranges to find satellite captures. In CrewAI, you assign this MCP tool to a dedicated Research Agent. This agent scans the Planet catalog for Landsat or Sentinel-2 imagery, adjusting cloud cover filters dynamically until it finds enough clear captures to form a baseline dataset. Once the Research Agent finishes, it passes the item IDs to an Analysis Agent equipped with `get_item_details`. This second agent cross-references the acquisition conditions and sun elevation, discarding any images that fail the strict criteria required for your specific GIS operation.

Delegate MCP Server subscriptions

The `create_subscription` tool pushes new satellite captures directly to your infrastructure. You can build a CrewAI Procurement Agent responsible solely for managing these data feeds. When a user requests continuous monitoring of a port facility, this agent configures the delivery destination and activates the webhook. A separate Monitor Agent can periodically check `list_subscriptions` to ensure the feeds remain active. If a delivery fails, the Monitor Agent alerts a Moderator Agent, which can then attempt to reset the connection or notify a human operator.

Analyze historical coverage patterns

The `get_search_statistics` tool generates a temporal histogram of available imagery over a target area. A CrewAI Planning Agent uses this data to figure out the optimal time of year to schedule high-resolution SkySat tasking. It looks at historical cloud cover patterns and acquisition frequency to predict the best collection windows. The agent verifies the available formats using `list_asset_types`. It ensures that the historical data actually includes the analytic bands needed for your project, preventing the crew from wasting time on visual-only datasets that cannot support mathematical analysis.

Setup guide

Set up Planet Labs MCP in CrewAI

Prerequisites

Python 3.10+ installed
crewai package (pip install crewai)
Active Vinkius subscription with a valid endpoint token

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke Planet Labs tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="Planet Labs Analyst",
    goal="Access and analyze Planet Labs data via MCP.",
    backstory="Expert analyst with direct Planet Labs access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent Planet Labs transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

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

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="Planet Labs Analyst",
        goal="Access and analyze Planet Labs data via MCP.",
        backstory="Expert analyst with direct Planet Labs access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent Planet Labs transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

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 CrewAI

You can pass the Vinkius endpoint directly into the mcps array when defining your agent. For more granular control, import MCPServerHTTP from crewai.mcp and use tool_filter to restrict which agent gets which tools.

Yes. CrewAI's shared memory allows a researcher agent to run quick_search and store the resulting item IDs. A downstream downloader agent can then read that memory and execute get_item_assets on the exact same files.

Use the tool_filter configuration to expose only read-only tools like get_item_details or list_item_types. Keep create_subscription assigned strictly to an authorized manager agent.

The get_search_results tool supports pagination. A CrewAI agent can be instructed to read the first page of results, evaluate the quality, and decide autonomously whether to request the next page or refine the search criteria.

The server handles your webhook URLs and cloud storage credentials entirely inside an isolated V8 sandbox. Authentication is managed at the endpoint level, and the ephemeral container terminates the moment the subscription is confirmed, leaving zero trace of your infrastructure details.

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