Skip to main content
Glama
Sign In
SkyFi MCP Server

SkyFi MCP Server

by seeincodes
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Hybrid

SkyFi MCP Server

npm version npm downloads

Official Model Context Protocol server for the SkyFi satellite imagery platform. Enables any AI agent to search, price, order, and monitor satellite imagery through conversational tool calls.

Quick Start (< 10 minutes)

1. Install

npm install skyfi-mcp@0.1.0

2. Configure

Create ~/.skyfi/config.json:

{ "api_key": "sk_your_skyfi_api_key" }

Or set the environment variable:

export SKYFI_API_KEY=sk_your_key

3. Run (Local STDIO)

npx skyfi-mcp

4. Connect

Claude Code / Claude Desktop:

{
  "mcpServers": {
    "skyfi": {
      "command": "npx",
      "args": ["skyfi-mcp"],
      "env": { "SKYFI_API_KEY": "sk_your_key" }
    }
  }
}

Claude.ai (remote MCP — no install needed):

  1. Open Claude.ai → Settings → Integrations → Add MCP Server

  2. Enter the server URL: https://skyfi-mcp.skyfi-xian.workers.dev/mcp

  3. Add your SkyFi API key as a custom header: X-SkyFi-API-Key: sk_your_key

  4. Save — Claude will automatically exchange your key for a session token

Remote (any framework):

# First request: send your API key to get a session token
POST https://skyfi-mcp.skyfi-xian.workers.dev/mcp
Header: X-SkyFi-API-Key: sk_your_key
→ Response includes X-MCP-Token header

# All subsequent requests: use the session token
POST https://skyfi-mcp.skyfi-xian.workers.dev/mcp
Header: X-MCP-Token: mcp_sess_<your_token>

Your raw API key is only sent once. The session token has a 4-hour idle TTL (extends on each request) and 7-day max lifetime.

Related MCP server: SkyFi MCP Server

Standout Differentiators

  • Reliability scorecard: generated operational snapshot at mcp-docs/STATUS.md (npm run status:refresh)

  • Golden demo workflow: maritime monitoring showcase at mcp-docs/GOLDEN_DEMO_MARITIME.md

  • Cost intelligence tool: recommend_archive_purchase ranks options by price/quality strategy with budget filtering

Authentication

Token Exchange (Remote)

The remote server uses a token exchange model to protect your SkyFi API key:

  1. Initialize — Send X-SkyFi-API-Key on your first request. The server validates it and returns an X-MCP-Token session token.

  2. Use — All subsequent requests use X-MCP-Token. Your raw API key never appears in agent traffic again.

  3. Expire — Session tokens expire after 4 hours idle or 7 days max. Re-send your API key to get a new one.

Service Tokens (Pipelines)

For automated pipelines that run unattended, create a long-lived service token:

# Call the create_service_token tool with an active session
→ Returns: mcp_svc_<token> (90-day lifetime, no idle expiry)

Service tokens support optional scopes (restrict which tools can be called) and budget caps (server-side spend limits).

Local (STDIO)

Local mode reads your API key from ~/.skyfi/config.json or SKYFI_API_KEY env var at startup. No token exchange needed.

Tools (19)

Category

Tools

Geocoding

geocode, reverse_geocode, get_bounding_box

Discovery

search_archive, explore_open_data

Pricing

estimate_archive_price, estimate_tasking_cost, check_capture_feasibility

Cost Intelligence

recommend_archive_purchase

Ordering

quote_archive_order, execute_archive_order, quote_tasking_order, execute_tasking_order

History

get_order_status, list_orders, fetch_order_image

Monitoring

setup_aoi_monitoring, create_webhook_subscription, get_notification_status

Order Safety

Orders use a two-step confirmation flow enforced server-side:

  1. Quote → returns price and quote_id (valid 15 min)

  2. Execute → requires quote_id + user_confirmed: true + idempotency_key

The execute_* tools cannot be called without all three fields. This is enforced at the schema level and cannot be bypassed by prompt injection.

Security

  • API key protection — Raw key sent once, exchanged for scoped token. Key encrypted at rest (AES-256-GCM) with derived keys (HKDF).

  • Key hashing — Usage metrics use HMAC-SHA-256 with a separate derived key. Not reversible without the server secret.

  • Per-request isolation — Each request creates an independent SkyFi client. No shared mutable auth state. One tenant's credentials cannot leak to another.

  • Rate limiting — Per-key: 100 calls/min, 20/10s burst. Daily caps: 10 orders, $10K spend.

  • Service token scoping — Optional tool restrictions and budget caps, enforced server-side.

  • Prompt injection defense — All inputs treated as data. String length caps (500 chars). Control character stripping. Order confirmation enforced server-side, not in prompts.

Framework Support

Framework

Transport

Guide

Google ADK

STDIO / HTTP+SSE

docs/integrations/google-adk.md

LangChain / LangGraph

STDIO / HTTP+SSE

docs/integrations/langchain.md

Vercel AI SDK

HTTP+SSE

docs/integrations/vercel-ai-sdk.md

Claude Web

HTTP+SSE

docs/integrations/claude-web.md

OpenAI

HTTP+SSE

docs/integrations/openai.md

Claude Code

STDIO / HTTP+SSE

docs/integrations/claude-code.md

Gemini

HTTP+SSE

docs/integrations/gemini.md

Compatibility matrix and transport expectations: docs/integrations/COMPATIBILITY.md

Simulation Mode

Test the full order flow without placing real orders:

SKYFI_SIMULATE=true npx skyfi-mcp

Or per-request: pass "simulate": true in quote/execute tool calls.

Deployment

Cloudflare Workers (live):

https://skyfi-mcp.skyfi-xian.workers.dev/mcp

Self-deploy:

npx wrangler deploy

Docker:

docker compose up

Development

npm install
npm run build        # Build with tsup
npm test             # Run test suite
npm run typecheck    # TypeScript check
npm run lint         # ESLint

License

MIT

Available Tools

19 tools
check_capture_feasibilityA

Analyze feasibility for a tasking order: satellite availability, revisit window, cloud cover forecast, and a plain-language summary. You MUST call this and present its output to the user before placing any tasking order. Precondition: call this before quote_tasking_order.

Inputs: aoi (required), sensor_type (required), desired_date_range.

create_webhook_subscriptionA

Register a webhook endpoint to receive push notifications when new imagery matching a monitoring rule is available. Requires an active monitor_id from setup_aoi_monitoring.

Inputs: monitor_id (required), endpoint_url (required), secret.

estimate_archive_priceA

Returns itemized pricing for a given archive order (scene, AOI, resolution) before commitment. Use this to give the user a cost estimate before generating a binding quote.

Inputs: aoi (required), scene_id (required), resolution_tier.

estimate_tasking_costA

Estimate the cost for a new satellite capture tasking order. Use this to give the user a cost preview before checking feasibility or generating a quote.

Inputs: aoi (required), sensor_type (required), resolution_tier.

execute_archive_orderA
Destructive

Place an archive order using a confirmed quote. Preconditions: (1) you must have a valid quote_id from quote_archive_order, (2) the user must have explicitly confirmed they want to proceed, (3) you must provide an idempotency_key (UUID) for safe retries. Do NOT call this tool autonomously — always wait for user confirmation.

Inputs: aoi (required), archive_id (required), user_confirmed (required), label.

execute_tasking_orderA
Destructive

Place a tasking order using a confirmed quote. Preconditions: (1) valid quote_id from quote_tasking_order, (2) explicit user confirmation, (3) idempotency_key (UUID). Do NOT call this tool autonomously — always wait for user confirmation.

Inputs: aoi (required), resolution (required), window_end (required), product_type (required), +4 more.

explore_open_dataA

Browse freely available datasets on SkyFi, filterable by provider and region. Use this when the user asks about free or open satellite data.

Inputs: page, limit, region, provider.

fetch_order_imageA

Return download URL and metadata for a completed order's imagery. Use this when the user wants to download or access imagery from a delivered order.

Inputs: order_id (required).

geocodeA

Forward geocoding: accepts a human-readable location string (e.g. 'Port of Rotterdam') and returns lat/lng coordinates. Use this when the user mentions a place by name and you need coordinates for search or ordering tools.

Inputs: query (required).

get_bounding_boxA

Returns a bounding box polygon for a named place, directly usable as an AOI in search and order tools. Use this to convert a place name into a GeoJSON polygon for subsequent tool calls.

Inputs: query (required).

get_notification_statusA

Check delivery history and status for webhook subscriptions. Use this to verify notifications are being delivered or to diagnose delivery failures.

Inputs: monitor_id, subscription_id.

get_order_statusA

Return current status and progress for an order by ID. Use this to check on a previously placed order.

Inputs: order_id (required).

list_ordersA

List the user's historical orders with filters for date range and status. Use this when the user asks about their past orders or order history.

Inputs: page, limit, status, date_range.

quote_archive_orderA

Generate a binding quote for an archive order. Returns a quote_id (valid 15 minutes) and a human-readable summary of what will be purchased and at what price. Present this to the user and wait for explicit confirmation before calling execute_archive_order.

Inputs: aoi (required), archive_id (required), overlap_sqkm (required), price_per_sqkm_usd (required), +1 more.

quote_tasking_orderA

Generate a binding quote for a new satellite capture tasking order. Returns a quote_id and summary. Precondition: call check_capture_feasibility first and present results to the user. Present this quote to the user and wait for confirmation before calling execute_tasking_order.

Inputs: aoi (required), resolution (required), window_end (required), product_type (required), +1 more.

recommend_archive_purchaseA

Rank candidate archive scenes by cost, quality, or a balanced strategy. Use this after search/pricing to pick the best scene under an optional budget.

Inputs: candidates (required), top_k, strategy, max_budget_usd.

reverse_geocodeA

Returns a place name for a given coordinate pair. Use this when you have lat/lng coordinates and need a human-readable location name.

Inputs: lat (required), lon (required).

search_archiveA

Search available satellite imagery by AOI, date range, resolution, and sensor type. Returns scenes with IDs, capture dates, cloud cover, preview URLs, and per-scene pricing. Use this as the first step when the user wants to find existing imagery.

Inputs: aoi (required), page, limit, date_range, +2 more.

setup_aoi_monitoringA

Configure recurring monitoring of an AOI for new imagery. Set sensor preferences, resolution requirements, and notification frequency. Use this when the user wants to be alerted when new imagery becomes available over a specific area.

Inputs: aoi (required), frequency, sensor_type, min_resolution_m.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Deploy Server
    One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

    TDQS

    A4/5.0

    Scored across 19 tools

    Disambiguation5/5

    Each tool has a clearly distinct purpose, with workflow steps (estimate vs quote vs execute) and resource types (archive vs tasking vs monitoring) cleanly separated. No two tools overlap in function; even related tools like geocode and get_bounding_box serve different output needs.

    Naming Consistency5/5

    All tool names follow a consistent verb_noun pattern in snake_case, using descriptive verbs (estimate, quote, execute, get, list) and clear noun targets (archive_order, tasking_order, notification_status). There is no mixing of styles or conventions.

    Tool Count4/5

    At 19 tools, the set is slightly above the ideal 3-15 range, but the breadth is justified by the platform covering archive ordering, tasking, monitoring, geocoding, and order management. Each tool earns its place in the workflow, and the count feels reasonable rather than bloated.

    Completeness4/5

    Core lifecycles are well-covered: search/explore, estimate, quote, execute, track, and retrieve for both archive and tasking orders, plus monitoring setup and geocoding utilities. Minor gaps exist, such as lacking explicit tools to cancel or update monitoring/webhook subscriptions, but these are non-critical and don't create dead ends.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Resources

    Related MCP Connectors

    Related MCP Servers

    • SkyFi MCP Server

      Davaakhatan
      A
      license
      Not graded
      quality
      D
      maintenance
      Enables AI agents to interact with SkyFi's geospatial data services for ordering satellite imagery, searching data catalogs, checking pricing and feasibility, and monitoring areas of interest.
      5 npm
      MIT

    • SkyFi MCP Server

      mfuechec
      F
      license
      Not graded
      quality
      Not graded
      maintenance
      Enables AI agents to search, order, and monitor satellite and geospatial imagery through SkyFi's API, including archive searches, pricing estimates, and order tracking.
      -

    • SkyFi MCP Server

      PSkinnerTech
      A
      license
      Not graded
      quality
      D
      maintenance
      Integrates SkyFi satellite imagery and OpenStreetMap services with AI applications to enable high-resolution image searching, ordering, and area monitoring. It provides 21 tools for geospatial tasks, including geocoding, tasking quotes, and satellite pass prediction.
      3
      MIT
    • Planet MCP

      Planet MCPofficial

      planetlabs
      A
      license
      Not graded
      quality
      C
      maintenance
      Enables AI agents to interact with the Planet API for satellite imagery ordering, subscriptions, and data management through natural language.
      17
      Apache 2.0