Planet Labs MCP Server for CrewAI 12 tools — connect in under 2 minutes
Connect your CrewAI agents to Planet Labs through Vinkius, pass the Edge URL in the `mcps` parameter and every Planet Labs tool is auto-discovered at runtime. No credentials to manage, no infrastructure to maintain.
ASK AI ABOUT THIS MCP SERVER
Vinkius supports streamable HTTP and SSE.
from crewai import Agent, Task, Crew
agent = Agent(
role="Planet Labs Specialist",
goal="Help users interact with Planet Labs effectively",
backstory=(
"You are an expert at leveraging Planet Labs tools "
"for automation and data analysis."
),
# Your Vinkius token. get it at cloud.vinkius.com
mcps=["https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"],
)
task = Task(
description=(
"Explore all available tools in Planet Labs "
"and summarize their capabilities."
),
agent=agent,
expected_output=(
"A detailed summary of 12 available tools "
"and what they can do."
),
)
crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)
* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure
About Planet Labs MCP Server
Connect your Planet Labs API to any AI agent and take full control of daily satellite imagery search, discovery, automated delivery, and imagery analysis through natural conversation.
When paired with CrewAI, Planet Labs becomes a first-class tool in your multi-agent workflows. Each agent in the crew can call Planet Labs tools autonomously, one agent queries data, another analyzes results, a third compiles reports, all orchestrated through Vinkius with zero configuration overhead.
What you can do
- Quick Search — Search for satellite imagery with geometry, date range, cloud cover, and sun elevation filters
- Saved Searches — Create and manage saved searches for recurring imagery monitoring workflows
- Search Results — Execute saved searches with pagination and sorting to retrieve imagery results
- Search Statistics — Get histograms of imagery availability by time interval for planning analysis
- Item Details — View detailed metadata for specific imagery items including acquisition conditions
- Asset Discovery — List all available asset types (visual, analytic, UDM2) for each imagery item
- Item Types — Browse all available satellite imagery types (PSScene, SkySat, RapidEye, Landsat, Sentinel-2)
- Asset Types — Understand available data products (true-color, surface reflectance, uncertainty masks)
- Cloud Coverage — Estimate clear area percentage before downloading imagery for quality assessment
- Subscriptions — List and create automated subscriptions for continuous cloud delivery of imagery
- Multi-Satellite Access — Search across PlanetScope (3-5m), SkySat (sub-meter), RapidEye (5m), Landsat (30m), and Sentinel-2 (10m)
- Global Daily Coverage — Access daily imagery of Earth landmass with 200+ PlanetScope satellites
The Planet Labs MCP Server exposes 12 tools through the Vinkius. Connect it to CrewAI in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.
How to Connect Planet Labs to CrewAI via MCP
Follow these steps to integrate the Planet Labs MCP Server with CrewAI.
Install CrewAI
Run pip install crewai
Replace the token
Replace [YOUR_TOKEN_HERE] with your Vinkius token from cloud.vinkius.com
Customize the agent
Adjust the role, goal, and backstory to fit your use case
Run the crew
Run python crew.py. CrewAI auto-discovers 12 tools from Planet Labs
Why Use CrewAI with the Planet Labs MCP Server
CrewAI Multi-Agent Orchestration Framework provides unique advantages when paired with Planet Labs through the Model Context Protocol.
Multi-agent collaboration lets you decompose complex workflows into specialized roles, one agent researches, another analyzes, a third generates reports, each with access to MCP tools
CrewAI's native MCP integration requires zero adapter code: pass Vinkius Edge URL directly in the `mcps` parameter and agents auto-discover every available tool at runtime
Built-in task delegation and shared memory mean agents can pass context between steps without manual state management, enabling multi-hop reasoning across tool calls
Sequential and hierarchical crew patterns map naturally to real-world workflows: enumerate subdomains → analyze DNS history → check WHOIS records → compile findings into actionable reports
Planet Labs + CrewAI Use Cases
Practical scenarios where CrewAI combined with the Planet Labs MCP Server delivers measurable value.
Automated multi-step research: a reconnaissance agent queries Planet Labs for raw data, then a second analyst agent cross-references findings and flags anomalies. all without human handoff
Scheduled intelligence reports: set up a crew that periodically queries Planet Labs, analyzes trends over time, and generates executive briefings in markdown or PDF format
Multi-source enrichment pipelines: chain Planet Labs tools with other MCP servers in the same crew, letting agents correlate data across multiple providers in a single workflow
Compliance and audit automation: a compliance agent queries Planet Labs against predefined policy rules, generates deviation reports, and routes findings to the appropriate team
Planet Labs MCP Tools for CrewAI (12)
These 12 tools become available when you connect Planet Labs to CrewAI via MCP:
create_saved_search
Accepts the same filter parameters as quick_search including geometry, date range, cloud cover, and item types. Returns a search ID that can be used with get_search_results to execute the search on demand. Essential for automated monitoring, change detection workflows, and recurring imagery retrieval. AI agents should use this when users ask "set up a search for new imagery over my field every week", "create a saved search for cloud-free images", or need to establish recurring imagery monitoring for a specific area. Create a saved search for continuous imagery monitoring
create_subscription
Accepts geometry, date range, cloud cover filters, item types, and delivery destination (cloud storage or webhook). Returns the created subscription with ID and status. Essential for setting up automated monitoring, establishing continuous data feeds for change detection, and ensuring regular imagery delivery for operational workflows. AI agents should use this when users ask "set up daily imagery delivery for my farm", "create a subscription for cloud-free images over this area", or need to establish automated imagery delivery for monitoring applications. Create a new subscription for continuous automated imagery delivery
get_cloud_coverage
Returns clear percentage, cloud percentage, and status information. Essential for quality assessment before downloading imagery, filtering cloudy images from analysis workflows, and ensuring usable imagery for visual interpretation. AI agents should use this when users ask "how cloudy is this image", "what percentage of this scene is clear", or need to assess imagery quality before committing to download. Estimate cloud coverage and clear area percentage for a specific imagery item
get_item_assets
Each asset includes download URLs, file sizes, and permissions. Essential for selecting the appropriate data product for analysis, downloading imagery for GIS processing, and understanding available data products. AI agents should use this when users ask "what assets are available for this image", "get download URLs for analytic imagery", or need to select specific asset types (visual for display, analytic for analysis) for download. List all available asset types (visual, analytic, UDM) for a specific imagery item
get_item_details
Essential for evaluating image quality before download, understanding acquisition conditions, and preparing orders for specific imagery. AI agents should reference this when users ask "show me details for this image", "what is the cloud cover and acquisition time for item X", or need to evaluate imagery quality before downloading. Get detailed metadata for a specific satellite imagery item
get_search_results
Supports pagination (page, page_size) and sorting (acquired asc/desc, published asc/desc). Returns imagery items with acquisition dates, cloud cover, geometry, and available asset types. Essential for retrieving results from pre-configured monitoring searches and executing recurring imagery queries. AI agents should use this when users ask "run my Weekly Farm Monitoring search", "get results from saved search X", or need to execute a saved search and retrieve the latest imagery results. Execute a saved search and retrieve imagery results
get_search_statistics
Essential for understanding imagery availability patterns, planning data collection schedules, and assessing temporal coverage for change detection analysis. AI agents should use this when users ask "how many images are available per month for my area", "show me imagery availability statistics", or need to understand temporal patterns of satellite coverage before setting up monitoring. Get statistical histograms of available imagery for an area and time period
list_asset_types
Returns asset type IDs, display names, and descriptions. Essential for selecting the appropriate data product for specific use cases (visual for visualization, analytic for NDVI calculation, UDM for quality filtering). AI agents should reference this when users ask "what asset types can I download", "difference between analytic and visual assets", or need to understand available data products for analysis. List all available asset types (visual, analytic, UDM, etc.) and their properties
list_item_types
Returns item type IDs, display names, and supported asset types for each. Essential for understanding available imagery sources, selecting appropriate resolution and coverage for analysis, and planning data acquisition strategies. AI agents should use this when users ask "what satellite imagery types are available", "compare PSScene vs SkySat resolution", or need to understand the full catalog of Planet imagery options. List all available satellite imagery item types and their supported assets
list_saved_searches
Returns search names, IDs, filter criteria, item types, and creation dates. Essential for managing monitoring workflows, reviewing existing search configurations, and selecting searches for execution. AI agents should reference this when users ask "show me all my saved searches", "list my monitoring configurations", or need to review existing saved searches before executing them. List all saved searches in your Planet account
list_subscriptions
Returns subscription names, IDs, filter criteria, delivery destinations, and status. Essential for monitoring automated imagery delivery, reviewing subscription configurations, and managing continuous data feeds. AI agents should reference this when users ask "show me all my subscriptions", "list automated imagery deliveries", or need to review existing subscription configurations. List all active imagery subscriptions for continuous cloud delivery
quick_search
Supports item types including PSScene (PlanetScope, 3-5m resolution, daily global coverage), SkySat (sub-meter resolution, high-detail), RapidEye (5m resolution, historical archive), Landsat 8/9 (30m resolution, USGS), and Sentinel-2 (10m resolution, ESA). Returns imagery items with acquisition dates, cloud cover percentages, sun elevation, instrument mode, geometry, and available asset types. Essential for satellite imagery discovery, change detection analysis, disaster monitoring, and agricultural assessment. AI agents should use this when users ask "find cloud-free imagery over this area from last month", "search for PSScene images of my farm", or need to discover available satellite imagery for a specific location and time period. Geometry must be provided as GeoJSON (Point, Polygon, or MultiPolygon). Date filtering uses the acquired property in ISO 8601 format. Cloud cover and sun elevation are filtered using the filter object with range operators. Search for satellite imagery from Planet Labs with geometry, date, and cloud cover filters
Example Prompts for Planet Labs in CrewAI
Ready-to-use prompts you can give your CrewAI agent to start working with Planet Labs immediately.
"Find cloud-free PSScene imagery over my farm boundary from the last 30 days."
"Show me what satellite imagery types are available and their resolutions."
"Create a daily subscription for cloud-free imagery over my monitoring area."
Troubleshooting Planet Labs MCP Server with CrewAI
Common issues when connecting Planet Labs to CrewAI through the Vinkius, and how to resolve them.
MCP tools not discovered
Agent not using tools
Timeout errors
Rate limiting or 429 errors
Planet Labs + CrewAI FAQ
Common questions about integrating Planet Labs MCP Server with CrewAI.
How does CrewAI discover and connect to MCP tools?
tools/list method. This means tools are always fresh and reflect the server's current capabilities. No tool schemas need to be hardcoded.Can different agents in the same crew use different MCP servers?
mcps list, so you can assign specific servers to specific roles. For example, a reconnaissance agent might use a domain intelligence server while an analysis agent uses a vulnerability database server.What happens when an MCP tool call fails during a crew run?
Can CrewAI agents call multiple MCP tools in parallel?
process=Process.parallel, each calling different MCP tools concurrently. This is ideal for workflows where separate data sources need to be queried simultaneously.Can I run CrewAI crews on a schedule (cron)?
crew.kickoff() method runs synchronously by default, making it straightforward to integrate into existing pipelines.Connect Planet Labs with your favorite client
Step-by-step setup guides for every MCP-compatible client and framework:
Anthropic's native desktop app for Claude with built-in MCP support.
AI-first code editor with integrated LLM-powered coding assistance.
GitHub Copilot in VS Code with Agent mode and MCP support.
Purpose-built IDE for agentic AI coding workflows.
Autonomous AI coding agent that runs inside VS Code.
Anthropic's agentic CLI for terminal-first development.
Python SDK for building production-grade OpenAI agent workflows.
Google's framework for building production AI agents.
Type-safe agent development for Python with first-class MCP support.
TypeScript toolkit for building AI-powered web applications.
TypeScript-native agent framework for modern web stacks.
Python framework for orchestrating collaborative AI agent crews.
Leading Python framework for composable LLM applications.
Data-aware AI agent framework for structured and unstructured sources.
Microsoft's framework for multi-agent collaborative conversations.
Connect Planet Labs to CrewAI
Get your token, paste the configuration, and start using 12 tools in under 2 minutes. No API key management needed.