Skip to main content
Glama
Foreclosure Data Hub MCP

Foreclosure Data Hub MCP

Official

search_unified_properties

Read-onlyIdempotent

Search legacy property feeds as one normalized, paginated list. Filter by state, county, zip, or address to find matching foreclosure records.

Instructions

Search legacy property feeds as one normalized, paginated list. Include at least one state, county, zip or address filter. Uses the same REST access and row allowances.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "search_unified_properties"
  }
}

Input Schema

NameRequiredDescriptionDefault
zipNoZip code filter. Can specify multiple.
modeNo
pageNoPage number (default: 1).
limitNoTotal listing rows across all groups: 1–100 paid or 1–10 during a new trial. Defaults to 25 when paid or 10 during a new trial. Choose a value within your remaining allowance.
stateNoState name or abbreviation. Can specify multiple.
countyNoCounty name filter. Can specify multiple (e.g., county=Cook&county=Lake).
addressNoProperty address filter (partial match). Can specify multiple.
page_sizeNoResults per page, 1–100 for paid keys or 1–10 for new trials. Defaults to 25 paid or 10 during a trial. Your remaining allowance may lower an omitted first-page size.
sale_daysNoMinimum lead time: sale_date_parsed must be later than today + N days (integer 1-365, unbounded above). ANDs with sale_date_start/sale_date_end. Listings without a parsed sale date stay included — an unscheduled sale cannot violate the bound. Unified mode only.
owner_nameNoOwner name filter (partial match on first or last name). Only applied to sources that expose owner fields.
sale_statusNoCanonical sale-status group: active, coming-soon, for-sale, postponed, cancelled, price-reduced, back-to-bank, new-listing, sold, mortgage-foreclosure, outbid, preview, pending, hard-to-sell, nos, vacant-lot, sale-held, none. Groups merge clearly-equivalent feed statuses — e.g. cancelled covers Cancelled/WITHDRAWN/Sale Invalid, sold covers Sold/Completed/3rd-party variants, postponed covers postpone*/On Hold. none matches listings with no reported status. Unified mode only.
est_value_maxNoMaximum estimated value (Market Valuation). Only applied to sources with an estimated value field.
est_value_minNoMinimum estimated value (Market Valuation). Only applied to sources with an estimated value field.
sale_date_endNoFilter by sale date end (YYYY-MM-DD).
pre_foreclosureNoSet true or 1 for scheduled-sale preforeclosures: sale date today or later (UTC), excluding REO-only feeds and REO asset types. Matches the dashboard filter. Listings without a known sale date, including early-stage defaults, are excluded. false or 0 disables the filter (default); other values return 400. A location filter is still required.
sale_date_startNoFilter by sale date start (YYYY-MM-DD).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

A3.7/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The annotations already establish read-only, idempotent, open-world, and non-destructive behavior. The description adds useful context beyond that: normalization across legacy feeds, pagination, the location-filter requirement, and row allowances, though 'same REST access and row allowances' remains vague.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is three short sentences and front-loads the core behavior and location-filter constraint. The trailing sentence about REST access and row allowances is vague and slightly wasteful, but overall it is efficient.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 16-parameter search tool, the description covers the essential location requirement and the notion of pagination. It omits sibling differentiation and does not explain how the many optional filters combine, leaving meaningful gaps for a tool of this complexity despite rich schema coverage.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 94%, so the schema already documents nearly all parameters. The description adds a meaningful cross-parameter requirement, at least one location filter, that the schema does not express because no parameters are marked required. It does not explain the semantics of the many optional filters, but most are covered by the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description gives a specific verb, 'Search,' and a specific resource, 'legacy property feeds,' presented as a normalized paginated list. It signals the tool's unified/legacy nature but does not name or distinguish it from the sibling search_properties tool.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It provides a hard prerequisite: include at least one state, county, zip, or address filter. However, it gives no explicit guidance on when to use this tool versus search_properties, single_source_data, or other search siblings, and no when-not guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.