geotap-mcp-server
ollect comprehensive environmental data from 80+ US federal sources (FEMA, EPA, USGS, NOAA, NRCS, USFWS, DOE, DOT, CDC, Census) for any US location. One tool returns flood zones, soils, wetlands, rainfall, water quality, contamination, seismic risk, infrastructure, ecology, energy, and demographics.
README
GeoTap MCP Server
Connect Claude, Cursor, Windsurf, and other AI tools to 80+ US federal environmental and infrastructure data sources.
GeoTap aggregates data from FEMA, USGS, EPA, NOAA, USDA, USFWS, DOT, Census, and more — accessible through the MCP (Model Context Protocol).
Web App: geotapdata.com — no code required, draw on a map and explore data visually.
Getting Started
Prerequisites
- Node.js (v18 or later) — download here
- An email address to register for your API key
Step 1: Get Your API Key
Go to geotapdata.com/developers and register with your email to get a free API key.
Your API key will be sent to your email. Save it — you'll need it in the next step.
Step 2: Set Up the MCP Server
Choose your AI tool below and follow the instructions. The MCP server is installed automatically via npx — no manual download needed.
<details open> <summary><strong>Claude Desktop</strong></summary>
- Open Claude Desktop
- Go to Settings (gear icon) → Developer → Edit Config
- This opens your
claude_desktop_config.jsonfile. Add the following (replaceyour-api-key-herewith your actual key):
{
"mcpServers": {
"geotap": {
"command": "npx",
"args": ["-y", "geotap-mcp-server"],
"env": {
"GEOTAP_API_KEY": "your-api-key-here"
}
}
}
}
Config file location:
- macOS:
~/Library/Application Support/Claude/claude_desktop_config.json- Windows:
%APPDATA%\Claude\claude_desktop_config.json
- Restart Claude Desktop completely (quit and reopen)
- You should see a hammer icon (🔨) in the chat input — that means GeoTap is connected
</details>
<details> <summary><strong>Claude Code (CLI)</strong></summary>
Run this command to add GeoTap to your Claude Code MCP servers:
claude mcp add geotap -- npx -y geotap-mcp-server
Then set your API key as an environment variable. Add this to your shell profile (~/.zshrc, ~/.bashrc, etc.):
export GEOTAP_API_KEY="your-api-key-here"
Restart your terminal, then start Claude Code. GeoTap tools will be available automatically.
</details>
<details> <summary><strong>Cursor</strong></summary>
- Open Cursor
- Go to Settings (⌘ + , on Mac, Ctrl + , on Windows) → search for "MCP"
- Click "Edit in settings.json" or add to your
.cursor/mcp.jsonfile:
{
"mcpServers": {
"geotap": {
"command": "npx",
"args": ["-y", "geotap-mcp-server"],
"env": {
"GEOTAP_API_KEY": "your-api-key-here"
}
}
}
}
- Restart Cursor
- Open the AI chat panel — GeoTap tools will appear in the available tools list
</details>
<details> <summary><strong>Windsurf</strong></summary>
- Open Windsurf
- Go to Settings → MCP Servers (or edit
~/.codeium/windsurf/mcp_config.jsondirectly) - Add:
{
"mcpServers": {
"geotap": {
"command": "npx",
"args": ["-y", "geotap-mcp-server"],
"env": {
"GEOTAP_API_KEY": "your-api-key-here"
}
}
}
}
- Restart Windsurf
</details>
<details> <summary><strong>Other MCP-Compatible Clients</strong></summary>
For any MCP client, the server can be run directly:
# Install globally
npm install -g geotap-mcp-server
# Run with your API key
GEOTAP_API_KEY=your-api-key-here geotap-mcp
The server communicates over stdio — point your MCP client to the geotap-mcp command with the GEOTAP_API_KEY environment variable set.
</details>
Step 3: Start Asking Questions
Once connected, ask your AI assistant to pull data for any US site. GeoTap collects from all 80+ federal sources at once — just give it a location and then ask whatever you want:
"Collect site data for 123 Main St, Austin TX"
Once the data comes back (~60-120 seconds), you can ask follow-up questions like:
- "Is this site in a flood zone?"
- "What soil types are here and what's the curve number?"
- "Are there any contamination concerns nearby?"
- "What's the 100-year rainfall?"
- "What permits would I need to develop this site?"
- "Summarize the key environmental risks"
Troubleshooting
| Problem | Solution |
|---|---|
| Server won't start / "GEOTAP_API_KEY is required" | Make sure your API key is set in the env block of your MCP config |
| "npx: command not found" | Install Node.js (v18+), which includes npx |
| Tools don't appear in Claude Desktop | Restart Claude Desktop completely (quit + reopen, not just close the window) |
| Rate limit errors | Wait a moment and retry — burst limits are per-minute |
Data Sources
| Agency | Data Available |
|---|---|
| FEMA | Flood zones, FIRM panels, flood insurance rate maps, floodway boundaries |
| USGS | Elevation (3DEP at 1m/10m/30m), geology, streamgages, groundwater, land use (NLCD), StreamStats, National Streamflow Statistics (NSS) |
| EPA | Water quality (ATTAINS), Superfund sites, brownfields, TRI toxic releases, USTs, NPDES outfalls |
| NOAA | Rainfall (Atlas 14), IDF curves, tide stations, climate projections (CMIP6), weather stations, radar |
| USDA/NRCS | Soils (SSURGO), curve numbers, hydrologic soil groups, TR-55 parameters |
| USFWS | Wetlands (NWI), endangered species, critical habitat |
| DOT | Bridges, tunnels, National Bridge Inventory |
| Census | Demographics, boundaries, TIGER geographic data |
| USACE | Dams, levees, navigation channels |
| NHD | Stream flowlines, hydrography, watershed boundaries (HUC-8/10/12) |
| Other | Power plants, mines, tribal lands, building footprints, and more |
Every response includes source attribution — the federal agency, dataset name, and reference URL.
Configuration
| Variable | Description | Required |
|---|---|---|
GEOTAP_API_KEY |
Your API key from registration | Yes |
GEOTAP_API_URL |
Custom API endpoint (advanced) | No |
Use Cases
Civil & Environmental Engineering
- Stormwater design: rainfall (Atlas 14, IDF curves, hyetographs), curve numbers, time of concentration, peak discharge
- Flood analysis: Bulletin 17C flood frequency, flow duration curves, regional regression estimates
- Watershed delineation and hydrologic modeling inputs (HEC-HMS, SWMM)
- Low-flow analysis for NPDES permits (7Q10, 7Q2, harmonic mean flow)
- Climate-adjusted design storms for infrastructure resilience
Real Estate & Development
- Environmental due diligence for property transactions
- Site feasibility and developability scoring (0-100 scale)
- Flood zone, wetland, and contamination screening
- Permit pathway analysis (Section 404, NPDES, floodplain development)
Environmental Consulting
- Phase I ESA desktop data gathering (EPA sites, water quality)
- Wetland delineation support (NWI + soils + hydrology)
- Endangered species habitat screening (USFWS critical habitat)
- Water quality impairment assessment (EPA ATTAINS 303(d) list)
Contributing
Contributions welcome! Please open an issue or pull request.
License
MIT
Links
- Web App: geotapdata.com
- Issues: GitHub Issues
- npm: geotap-mcp-server
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。