SkyFi MCP Server
Provides tools for converting place names to coordinates and WKT polygons (osm_geocode), reverse geocoding (osm_reverse_geocode), and searching for nearby features like airports or ports (osm_search_nearby).
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
SkyFi MCP Server
A production-ready MCP server for SkyFi's satellite imagery Platform API. Search 150+ satellites from 12+ providers, compare pricing, and order archive or tasking imagery — all through natural language with any AI agent.
SkyFi aggregates imagery from Planet, Vantor, ICEYE, Umbra, Satellogic, and others into a single API with transparent pricing and no contracts. This MCP server makes that API accessible to Claude, GPT, Gemini, LangChain, and any MCP-compatible agent.
Architecture
graph LR
A[AI Agent] -->|MCP Protocol| B[SkyFi MCP Server]
B -->|REST API| C[SkyFi Platform API]
B -->|Nominatim| K[OpenStreetMap]
C --> D[Planet]
C --> E[Vantor]
C --> F[ICEYE]
C --> G[Umbra]
C --> H[Satellogic]
C --> I[Sentinel-1/2]
C --> J[12+ more...]Related MCP server: Planet MCP
Quick Start (< 5 minutes)
1. Install
pip install skyfi-mcp
# or from source:
git clone https://github.com/jpwilson/skyfi-mcp.git
cd skyfi-mcp && pip install -e .2. Configure
export SKYFI_API_KEY=your_api_key # Get one at https://app.skyfi.com3. Run
# Remote server (production)
skyfi-mcp
# → Listening at http://localhost:8000/mcp
# Local stdio (development)
SKYFI_MCP_TRANSPORT=stdio skyfi-mcp4. Connect your agent
Claude Desktop — add to claude_desktop_config.json:
{
"mcpServers": {
"skyfi": {
"url": "http://localhost:8000/mcp"
}
}
}Claude Code:
claude mcp add skyfi http://localhost:8000/mcp5. Try it (free)
"Find free Sentinel-2 imagery over the Amazon basin"
This uses open data ($0) — no credit card needed.
Tools (20)
Tool | Description |
SkyFi API | |
| Check account status, budget, payment method |
| Search archive imagery by location, date, sensor, provider |
| Get full details for an archive image |
| Get pricing by AOI, product type, provider |
| Create tasking feasibility check |
| Poll feasibility results and provider windows |
| Satellite pass prediction for tasking timing |
| Stage an archive order (shows price, requires confirmation) |
| Stage a tasking order (shows price, requires confirmation) |
| Execute a staged order (this commits money) |
| List orders with status/type filters |
| Get order details |
| Redeliver completed order to different cloud bucket |
| Get download URLs for completed orders |
| Set up AOI monitoring with webhook alerts |
| List active monitoring notifications |
| Get or delete a notification |
OpenStreetMap | |
| Convert place names to coordinates + SkyFi-ready WKT polygons |
| Convert coordinates to place names and addresses |
| Find features (airports, ports, etc.) near a location |
Ordering Safety
Orders use a two-step confirmation pattern:
Stage —
skyfi_create_archive_orderorskyfi_create_tasking_ordercalls the API and returns a price summaryConfirm — Only
skyfi_confirm_ordermarks the order as human-approved
Order: VANTOR 30cm DAY, 12.4 sq km, $847. Deliver to S3. Confirm?Free open-data orders ($0 Sentinel-1/2) still show confirmation but note "Free — no charge."
Tasking Workflow
1. skyfi_create_feasibility → get feasibility ID
2. skyfi_get_feasibility → poll for provider windows
3. skyfi_predict_passes → (optional) check satellite timing
4. skyfi_create_tasking_order → stage with selected provider/window
5. skyfi_confirm_order → execute after human approvalProvider-specific: Planet supports provider_window_id selection from feasibility results.
AI Provider Integration
Provider | Method | Example |
Claude Desktop | MCP config | |
Claude Code |
| |
OpenAI | Function calling | |
Anthropic SDK | Tool use | |
Google Gemini | Function calling | |
Google ADK | MCPToolset | |
LangChain | MCP adapter | |
Vercel AI SDK | MCP client |
Deployment
Railway (recommended for cloud)
railway login && railway init
railway variables set SKYFI_API_KEY=your_key
railway up
# → https://your-project.up.railway.app/mcpDocker
docker build -t skyfi-mcp .
docker run -p 8000:8000 -e SKYFI_API_KEY=your_key skyfi-mcpOr with docker-compose:
echo "SKYFI_API_KEY=your_key" > .env
docker-compose upConfiguration
Auth is resolved in priority order:
X-Skyfi-Api-Keyrequest header (cloud deployment)SKYFI_API_KEYenvironment variableConfig file at
~/.skyfi/config.json(orSKYFI_CONFIG_PATH)
Environment variables:
Variable | Default | Description |
| — | SkyFi Platform API key |
|
| Server bind host |
|
| Server bind port |
|
| Transport: |
|
| API base URL override |
AOI Constraints
Format: WKT
POLYGON(convex)Max vertices: 500
Max area: 500,000 sq km
Coordinates: longitude latitude (WGS84)
Development
# Install with dev dependencies
pip install -e ".[dev]"
# Run tests
pytest
# Run with coverage
pytest --cov=skyfi_mcp --cov-report=term-missing
# Lint
ruff check src/ tests/
# Type check
mypy src/
# Security scan
bandit -r src/Documentation
Contributing
Fork the repository
Create a feature branch (
git checkout -b feature/amazing-feature)Write tests for new functionality
Run the full test suite (
pytest)Run linting and type checks (
ruff check . && mypy src/)Commit with descriptive messages
Open a pull request
License
MIT — see LICENSE.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
Paid intelligence tools for AI agents across risk, finance, property, logistics and more.
Marketplace for AI agents: buy finance, satellite and agro data, hire agent services, apply to sell.
One API key, dozens of capabilities for your AI agent. Zero provider auth.
Verified, sourced, real-time intelligence layer for AI agents.
Related MCP Servers
- FlicenseNot gradedqualityNot gradedmaintenanceEnables AI agents to search, order, and monitor satellite and geospatial imagery through SkyFi's API, including archive searches, pricing estimates, and order tracking.-

Planet MCPofficial
AlicenseNot gradedqualityCmaintenanceEnables AI agents to interact with the Planet API for satellite imagery ordering, subscriptions, and data management through natural language.18Apache 2.0- AlicenseAqualityDmaintenanceEnables AI agents to search, price, order, and monitor satellite imagery from the SkyFi platform through conversational tool calls.195 npmMIT
- AlicenseAqualityBmaintenanceEnables AI agents to query Earth observation data, satellite imagery, active fires, and weather via natural language, returning interactive maps and briefs.12MIT