mcpField
L
landbenchmark-mcp

landbenchmark-mcp

Local
github.com/winds3753Business & Marketing0Updated 13w ago
Repository

About landbenchmark-mcp

landbenchmark-mcp is an MCP server for AI agents conducting satellite-based land due diligence. Its analyze_parcel tool returns a cited green, caution, or walk-away assessment of parcel signals.

Key features

  1. 01Analyze parcel coordinates or geometry
  2. 02Assess flooding and hazards
  3. 03Evaluate slope, buildability, soil, and access
  4. 04Choose lite or full analysis
  5. 05Return cited findings and report link

Use cases

  1. 01Screen land before a purchase
  2. 02Review parcel risks from a map location
  3. 03Request a deeper multi-year satellite report

MCP support

Exposes the analyze_parcel tool to MCP clients. It accepts parcel coordinates or GeoJSON geometry and returns a plain-text verdict with flagged signals and a link to the full report.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "winds3753-landbenchmark": {
      "command": "npx",
      "args": [
        "-y",
        "landbenchmark-mcp"
      ],
      "env": {
        "TERRAIN_API_KEY": "<TERRAIN_API_KEY>",
        "TERRAIN_BASE_URL": "<TERRAIN_BASE_URL>"
      }
    }
  }
}
Run commandnpx -y landbenchmark-mcp
Environment variables to set
TERRAIN_API_KEYSecretLandBenchmark API key (create one at https://www.landbenchmark.com/account).
TERRAIN_BASE_URLLandBenchmark base URL, e.g. https://www.landbenchmark.com

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npmlandbenchmark-mcp0.1.1

Tools

1

Saved tool list · updated 3w ago

ParameterTypeRequiredDescription
latnumberNoLatitude of the parcel (WGS84).
lonnumberNoLongitude of the parcel (WGS84).
modeenumNolite = fast open-data + satellite flood-history scan (~1 min, default); full = deep multi-year satellite report (~3-4 min).lite | full
labelstringNoOptional name for the parcel.
geometryanyNoGeoJSON Polygon or Point (alternative to lat/lon).

Details

From the project README

landbenchmark-mcp

An MCP server that lets AI agents run satellite land due-diligence through LandBenchmark. It exposes one tool, analyze_parcel, that returns a green / caution / walk-away verdict with cited signals (flooding, slope & buildability, soil, hazards, access) for any parcel.

Why

When someone asks their AI assistant "is this land any good to buy?", the agent can call LandBenchmark and answer with observed, cited satellite data instead of guessing.

Setup

  1. Get an API key at landbenchmark.com/account → API keys.
  2. Add the server to your MCP client config:
{
  "mcpServers": {
    "terrain": {
      "command": "npx",
      "args": ["-y", "landbenchmark-mcp"],
      "env": {
        "TERRAIN_API_KEY": "tk_live_...",
        "TERRAIN_BASE_URL": "https://www.landbenchmark.com"
      }
    }
  }
}

Both env vars are required. (TERRAIN_* is the internal engine name — LandBenchmark runs on the Terrain analysis engine.) TERRAIN_BASE_URL has no default on purpose: every request sends your API key to that host in an Authorization header, so the server refuses to start rather than guess where it goes. It also refuses to send a key over plain http:// to anything but localhost.

Works with any MCP-capable client — Claude Desktop, Claude Code, and agent frameworks.

Tool: analyze_parcel

ParamTypeNotes
lat, lonnumberParcel centre (WGS84). Provide these or geometry.
geometryGeoJSONPolygon or Point (alternative to lat/lon).
labelstringOptional parcel name.
mode"lite" | "full"lite (default) ≈ 1 min; full = deep multi-year satellite report ≈ 3–4 min.

Returns a plain-text verdict summary with the flagged signals and a link to the full report.

Build

npm install
npm run build   # → dist/index.js
npm test        # verifies the API-key safety guard

Links

Informational only — not a survey, flood determination, or a substitute for on-site inspection and professional advice.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.