Stormaxis Mcp

Created By
StormAxis3 months ago
Real-time US storm intelligence for roofing and restoration contractors. Scored opportunities, property targeting, canvass routing, and FEMA claim data from live NOAA/SPC feeds.
Overview

StormAxis MCP Server

npm version MCP Compatible License: MIT API Status

Give your AI agent real-time US storm intelligence. StormAxis connects Claude, GPT, and any MCP-compatible agent to live NOAA storm data, scored contractor opportunities, property targeting lists, and canvass route optimization — purpose-built for roofing and restoration contractors.


What it does

StormAxis watches every storm in the United States in real time. When a qualifying hail or wind event hits, it automatically scores it (0–100) based on severity, local property values, roof age, and historical claim rates — then surfaces the best opportunities to your agent.

Your AI agent can:

  • Ask "What are the best storm opportunities in Texas right now?" and get a ranked list with estimated revenue
  • Pull a property target list for any ZIP code hit by a scored storm
  • Get H3-optimized canvass clusters so field crews know exactly where to knock doors first
  • Check insurance claim propensity by state before committing resources to a new market
  • Subscribe to webhooks that fire the moment a qualifying storm lands in your territory

Quickstart

1. Get a Partner API key

Sign up at stormaxis.io/partner. MCP access requires Growth tier ($199/mo) or above.

2. Add to Claude Code

claude mcp add stormaxis \
  --transport sse \
  --url https://stormaxis.io/api/mcp/sse \
  --header "X-API-Key: YOUR_API_KEY"

3. Make your first call

Ask Claude: "Check the StormAxis pipeline status."

You should see pipeline_active: true and a latest_event_time within the last 48 hours. You're live.


Alternative Setup Methods

Claude Desktop (via mcp-remote)

Add to ~/Library/Application Support/Claude/claude_desktop_config.json:

{
  "mcpServers": {
    "stormaxis": {
      "command": "npx",
      "args": ["-y", "mcp-remote", "https://stormaxis.io/api/mcp/sse"],
      "env": {
        "MCP_REMOTE_HEADER_X_API_KEY": "YOUR_API_KEY"
      }
    }
  }
}

Standalone npm server (stdio)

npm install -g stormaxis-mcp

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "stormaxis": {
      "command": "stormaxis-mcp",
      "env": {
        "STORMAXIS_API_KEY": "YOUR_API_KEY"
      }
    }
  }
}

Local development

git clone https://github.com/stormaxis/stormaxis-mcp
cd stormaxis-mcp
cp .env.example .env          # add your API key
npm install
npm run build
npm start

Tool Reference

Full mapping of MCP tools to their underlying Partner API endpoints.

MCP ToolREST EndpointTierKey ParametersDescription
get_storm_overviewGET /api/v1/partner/storm/overviewGrowthUS storm snapshot — counts by type, top states, SPC outlook
get_top_opportunitiesGET /api/v1/partner/opportunities/topGrowthstate? min_score? limit?Last 30 days of storms ranked by opportunity score (0–100)
get_storm_scoreGET /api/v1/partner/storm/{id}/scoreGrowthstorm_idFull composite score breakdown: storm relevance, property economics, replacement probability
search_propertiesGET /api/v1/partner/properties/{zip}Professionalzip_code owner_type? min_roof_age? min_sqft? limit?Owner + property records for door-knock targeting
get_canvass_clustersGET /api/v1/partner/clusters/{storm_id}Professionalstorm_id min_score? limit?H3 hexagonal canvass zones ranked by doors/hour × owner-occupancy
get_insurance_propensityGET /api/v1/partner/analytics/insurance-propensityGrowthstate?Claim culture score + avg payout per state
get_fema_claimsGET /api/v1/partner/fema/claimsProfessionalstate year_start? year_end?Historical NFIP flood claims aggregated by ZIP
get_pipeline_statusGET /api/v1/partner/pipeline/statusGrowthData freshness and ingestion health check

Score Components (get_storm_score)

ComponentWhat it measures
storm_relevance_scoreRecency, magnitude, NWS confirmation
property_economics_scoreAvg property value, roof age, density
replacement_probabilityML prediction of claim conversion likelihood

Prompts

The server ships two pre-built prompt templates that chain multiple tools into a single natural-language request:

PromptArgumentsDescription
storm_assessmentstate (default: TX)Full briefing: overview → top opportunities → score breakdown → property targeting
property_searchzip_code (default: 76109)Find older-roof properties in a ZIP with active storm context

Example Agent Workflows

Daily Sales Briefing

1. get_storm_overview           → What's active nationally?
2. get_top_opportunities        → Which markets rank highest today?
3. get_insurance_propensity     → Which states convert claims best?
4. get_storm_score(top_id)      → Deep-dive on #1 opportunity

Field Operations Planning

1. get_top_opportunities(state="TX")   → Identify top TX storm
2. get_canvass_clusters(storm_id)      → Get optimized zones
3. search_properties(zip_code)         → Pull door-knock list per zone

New Market Assessment

1. get_insurance_propensity(state)               → How claim-friendly is this state?
2. get_fema_claims(state)                        → Historical flood risk by ZIP
3. get_top_opportunities(state, min_score=50)    → Any current opportunities?

Pricing

TierPriceDaily API CallsMCP AccessTools AvailableWebhooks
SandboxFree100NoDashboard onlyNo
Growth$199/mo5,000Yesget_storm_overview, get_top_opportunities, get_storm_score, get_insurance_propensity, get_pipeline_statusNo
Professional$499/mo25,000YesAll 8 toolsNo
Enterprise$1,499+/mo100,000YesAll tools + Bulk ExportIncluded

Overage: $0.05–$0.08 per 1,000 calls on Growth and above.

Webhook Subscriptions (storm.scored, storm.gold, storm.updated, properties.available, pipeline.alert) are available on Enterprise tier and are included in the base price. See /docs/webhooks.md.


Error Reference

ErrorCause
Missing X-API-Key headerNo API key in request
Invalid or inactive API keyKey not found or revoked
API key expiredKey has passed expiration date
MCP access requires Growth tier or aboveSandbox key — upgrade at stormaxis.io/partner
Daily limit of N calls reachedRate limit hit — resets midnight UTC
Storm {id} not foundInvalid or expired storm ID
Database unavailableTransient backend error — retry with exponential backoff

Data Sources

SourceData TypeRefresh Frequency
NOAA/NWS Storm DataVerified storm eventsContinuous
SPC Convective OutlooksRisk forecastsEvery 15 minutes
MRMS (Multi-Radar Multi-Sensor)Hail size validationEvery 6 hours
US County Assessor RecordsProperty dataMonthly
FEMA NFIP ClaimsFlood insurance historyAnnual

Storm opportunity scores are recomputed every 6 hours as new events are confirmed.


Examples


Docs


Support

Server Config

{
  "mcpServers": {
    "stormaxis": {
      "transport": "streamable-http",
      "url": "https://stormaxis.io/api/mcp",
      "headers": {
        "X-API-Key": "YOUR_API_KEY"
      }
    }
  }
}
Project Info
Created At
3 months ago
Updated At
2 months ago
Author Name
StormAxis
Star
-
Language
-
License
-
Category

Recommend Servers

View All
//beforeyouship — LLM Cost Modeling From Your Editor
@Indiegoing

Query realistic LLM cost models without leaving your editor. beforeyouship models the **true monthly cost** of an LLM app architecture — retries, prompt caching, batch discounts, infra overhead, and 3×/10× growth — across GPT-5.x, Claude, Gemini, DeepSeek, and more. Not a token calculator: a planning tool for the design phase, before you commit to a stack. **No API key needed to try it** — demo mode covers the six free-tier models. A Pro key from [beforeyouship.dev](https://beforeyouship.dev) unlocks the full 18-model catalog. ## What you can ask - "How much will a RAG chatbot cost at 10,000 requests/day?" - "Compare Claude Haiku vs Gemini Flash pricing for my workload" - "What's the cheapest model for a multi-step agent at scale?" - "Show me current per-token prices for Anthropic models" ## Tools ### `estimate_cost` Full cost model for an architecture at a given usage level. Returns Naive / Realistic / Worst Case monthly cost per model, 3×/10× growth scenarios, and an opinionated recommendation with reasoning. ### `get_model_prices` Current per-1M-token pricing — input, output, cached input, batch — with context windows and staleness metadata. ### `list_archetypes` Seven preset architecture patterns (simple chatbot, chatbot with history, RAG pipeline, multi-model router, coding assistant, document processor, multi-step agent) used as starting points for estimates. ## Setup **Claude Code:** ​```bash claude mcp add --transport http beforeyouship https://beforeyouship.dev/api/mcp ​``` **Cursor / other clients** — add a remote server: ​```json { "mcpServers": { "beforeyouship": { "type": "streamable-http", "url": "https://beforeyouship.dev/api/mcp" } } } ​``` Add an `Authorization: Bearer bys_...` header with a Pro key for the full catalog. ## Try it > Estimate the monthly cost of a RAG pipeline at 10,000 requests/day

8 hours ago
Linkpulse

11 hours ago
Tavily Mcp
@tavily-ai

JavaScript
a year ago
Shippo
@Shippo

16 hours ago