Parcel Discovery

Find parcels that match a brief (state and county, acreage, land use, value, last sale) and return a clean shortlist with owner, acreage, value and location.

An area and a set of criteria · Tools: parcel_coverage, parcel_search, start_run, get_run · 25 lookups per page of up to 100 parcels; empty pages and parcel_coverage are free.

mkdir -p ~/.claude/skills/isopleth-parcel-discovery && curl -fsSL https://isopleth.dev/templates/parcel-discovery/SKILL.md -o ~/.claude/skills/isopleth-parcel-discovery/SKILL.md

Example prompt

Or pick the parcel_discovery prompt from the Isopleth MCP server in your client.

How it works

1. Call parcel_coverage for the state (free) to confirm it is covered and which columns it publishes (owner names, values and sale data vary by state).
2. Call parcel_search with the state, county and the criteria as filters (acres_min/acres_max, land_use, value_min/value_max, sale_date_min, year_built_max, zip). Use limit 100: a page costs the same whatever its size, and an empty page is free.
3. If has_more is true and the user wants everything, either pass next_cursor for the next page or, for more than a few pages, call start_run with kind "search", the same search body and max_pages (and a max_lookups budget), then poll get_run.
4. Present a table sorted by the user's priority (acreage by default): parcel number, situs address, owner, land use, acres, assessed value, last sale price and date.
5. Say how many parcels matched in total, how many pages were read, and the lookups spent.

Fields used

Parcel record columns (published columns vary by state; see coverage): parcelnumb, address, scity, owner, usedesc, gisacre, parval, landval, saleprice, saledate, lat, lon.

Tool call

What the agent sends to parcel_search:

{
  "state": "NC",
  "county": "Wake",
  "acres_min": 20,
  "acres_max": 100,
  "land_use": "agricultural",
  "value_max": 500000,
  "limit": 100
}

Output

A ranked table of parcels with the columns above, a one-line summary of the filters used, and the total matched. Note any column the state does not publish.

SKILL.md

Save this as isopleth-parcel-discovery/SKILL.md in your agent's skills folder (for Claude Code, ~/.claude/skills/), or download it.

---
name: isopleth-parcel-discovery
description: Find parcels that match a brief (state and county, acreage, land use, value, last sale) and return a clean shortlist with owner, acreage, value and location. Uses the Isopleth MCP server (https://api.isopleth.dev/mcp).
---

# Parcel Discovery

Find parcels that match a brief (state and county, acreage, land use, value, last sale) and return a clean shortlist with owner, acreage, value and location.

## Requirements

- The Isopleth MCP server connected at `https://api.isopleth.dev/mcp` with an API key in the `Authorization: Bearer` header (see https://isopleth.dev/docs/mcp).
- Tools used: `parcel_coverage`, `parcel_search`, `start_run`, `get_run`.
- Cost: 25 lookups per page of up to 100 parcels; empty pages and parcel_coverage are free.

## Steps

1. Call parcel_coverage for the state (free) to confirm it is covered and which columns it publishes (owner names, values and sale data vary by state).
2. Call parcel_search with the state, county and the criteria as filters (acres_min/acres_max, land_use, value_min/value_max, sale_date_min, year_built_max, zip). Use limit 100: a page costs the same whatever its size, and an empty page is free.
3. If has_more is true and the user wants everything, either pass next_cursor for the next page or, for more than a few pages, call start_run with kind "search", the same search body and max_pages (and a max_lookups budget), then poll get_run.
4. Present a table sorted by the user's priority (acreage by default): parcel number, situs address, owner, land use, acres, assessed value, last sale price and date.
5. Say how many parcels matched in total, how many pages were read, and the lookups spent.

## Arguments (example `parcel_search` call)

```json
{
  "state": "NC",
  "county": "Wake",
  "acres_min": 20,
  "acres_max": 100,
  "land_use": "agricultural",
  "value_max": 500000,
  "limit": 100
}
```

## Output

A ranked table of parcels with the columns above, a one-line summary of the filters used, and the total matched. Note any column the state does not publish.

Every value carries its source, license and attribution. Keep the source next to each value, and show the attributions if you share the results.

Connect your agent

https://api.isopleth.dev/mcp

https://api.isopleth.dev/mcp

claude mcp add --transport http isopleth https://api.isopleth.dev/mcp

claude mcp add --transport http isopleth https://api.isopleth.dev/mcp --header "Authorization: Bearer $ISOPLETH_KEY"

{
  "mcpServers": {
    "isopleth": {
      "url": "https://api.isopleth.dev/mcp"
    }
  }
}

code --add-mcp '{"name":"isopleth","type":"http","url":"https://api.isopleth.dev/mcp"}'

{
  "servers": {
    "isopleth": {
      "type": "http",
      "url": "https://api.isopleth.dev/mcp"
    }
  }
}

codex mcp add isopleth --url https://api.isopleth.dev/mcp

codex mcp add isopleth --url https://api.isopleth.dev/mcp --bearer-token-env-var ISOPLETH_KEY

{
  "mcpServers": {
    "isopleth": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://api.isopleth.dev/mcp",
        "--header",
        "Authorization:${ISOPLETH_AUTH}"
      ],
      "env": {
        "ISOPLETH_AUTH": "Bearer YOUR_ISOPLETH_KEY"
      }
    }
  }
}

{
  "mcpServers": {
    "isopleth": {
      "serverUrl": "https://api.isopleth.dev/mcp"
    }
  }
}

https://api.isopleth.dev/mcp

Authorization: Bearer $ISOPLETH_KEY