[go: up one dir, main page]

Commercial real estate facts that cite their source

Every number has a source.

Each fact names its method, its source document and record, and the rights that travel with it.

Connect Claude or ChatGPT What is hosted

registry_getas of 2026-11-01

1000 LOUISIANA ST, HOUSTON TX 77002

fl:parcel:us-48201:0011440000001

Market value
$303,755,215
1 real_acct.txt acct 0011440000001
Improvement area
1,871,418 SF
1 real_acct.txt acct 0011440000001
Year built
1983
1 real_acct.txt acct 0011440000001
Building class
A
2 building_other.txt acct 0011440000001 bld_num 1
  1. Harris Central Appraisal District: Real property appraisal roll export (Real_acct_owner.zip), retrieved 2026-11-02
  2. Harris Central Appraisal District: Real property building and land export (Real_building_land.zip), retrieved 2026-11-02

The worked example

Commercial parcels on the hosted API
1,099,275
Counties hosted
87
Texas counties hosted
18
Calculators
26

What FactLot does for you, by who you are

Texas property-tax consultants, attorneys and in-house tax staff

A commercial account's roll values by year (earlier years with Pro or Team), candidate comparables under a stated rule, and the unequal-appraisal arithmetic in a workbook you can review and share. Each figure is cited to the district's file.

FactLot is software. It is not a property tax consultant under Texas Occupations Code chapter 1152, does not prepare, file or advise on protests, and does not represent owners before an appraisal review board.

Texas tax evidence

People building commercial real estate agents

Make your agent's numbers checkable: calculators with audit trails, quote-on-page verification, and facts that cite their document and licence. Free, no key.

MCP server What is in it

People who use Claude or ChatGPT for commercial real estate

Ask your assistant which company owns a commercial building, a few of its other parcels (all of them with Pro or Team) and what the building is assessed at. Every answer cites the public record.

Connect Claude or ChatGPT What is hosted

An open fact layer for commercial real estate AI agents

AI agents are fluent about commercial real estate, and often wrong about the facts.

FactLot gives them cited facts and deterministic math: 26 calculators with audit trails, canonical IDs, and a public-record registry where every fact points at the document it came from.

Add to your agent Read the source Pricing

One line for any MCP client, no API key: npx -y https://github.com/9mp96ygnbk-alt/factlot/releases/download/v0.5.0/factlot-mcp-standalone-0.5.0.tgz. Or connect with no install: remote MCP at https://api.factlot.com/mcp, free at 60 requests a minute. Claude Code users can install the plugin with twelve CRE skills: /plugin marketplace add 9mp96ygnbk-alt/factlot. Listed in the official MCP Registry as io.github.9mp96ygnbk-alt/factlot.

How it works

How a FactLot answer is made Your agent or app calls a FactLot tool. FactLot's calculators, IDs and registry produce the answer. The answer is a cited record: each value names the file and the record it was read from. The citation points at the public source. 01 · YOUR AGENT OR APP TOOL CALL registry_get( "fl:parcel:us-48201:…" ) MCP · REST · PYTHON WHAT COMES BACK the value the method or formula ID the source and record the rights that travel 02 · FACTLOT Calculators steps · warnings · formula ID calc.net_effective_rent@1 IDs parcels · entities · documents fl:parcel:us-48201:0011440000001 Registry parcel › owner of record › entity from public records only 03 · THE CITED RECORD parcel.market_value $303,755,215 [1] real_acct.txt acct 0011440000001 parcel.year_built 1983 [1] real_acct.txt acct 0011440000001 METHODpublic_record AS OF2026-11-01 RIGHTSlicence · AI use 04 · THE PUBLIC SOURCE real_acct.txt acct 0011440000001 Harris Central Appraisal District RETRIEVED 2026-11-02 How a FactLot answer is made Your agent or app calls a FactLot tool. FactLot's calculators, IDs and registry produce the answer. The answer is a cited record: each value names the file and the record it was read from. The citation points at the public source. 01 · YOUR AGENT OR APP TOOL CALL registry_get( "fl:parcel:us-48201:0011440000001" ) 02 · FACTLOT Calculators steps · warnings · formula ID IDs fl:parcel:us-48201:0011440000001 Registry parcel › owner of record › entity 03 · THE CITED RECORD parcel.market_value $303,755,215 [1] real_acct.txt acct 0011440000001 parcel.year_built 1983 [1] real_acct.txt acct 0011440000001 04 · THE PUBLIC SOURCE real_acct.txt acct 0011440000001 Harris Central Appraisal District RETRIEVED 2026-11-02

An agent calls a tool instead of doing the math in context, then reports the formula and points to the steps. The inputs and values below are the project's shared test vector for net effective rent (spec/vectors/calc/net_effective_rent.json), which both the TypeScript and Python SDKs must reproduce to the last digit. The steps array is elided.

Agent guide: which tool to call when

1. The agent calls calc_net_effective_rent

{
  "schedule": {
    "commencement_date": "2026-01-01",
    "term_months": 120,
    "area_sf": 10000,
    "starting_rent_psf_annual": 40,
    "abated_months": [1, 2, 3, 4, 5, 6]
  },
  "ti_allowance_psf": 50,
  "leasing_commissions": 100000,
  "discount_rate_annual": 0.08
}

2. The tool answers with the value, the formula, and an audit trail

{
  "value": {
    "total_rent_due": 3799999.62,
    "total_landlord_costs": 600000,
    "effective_rent_psf": 38,
    "net_effective_rent_psf": 32,
    "pv_rent": 2568980.49,
    "discounted_net_effective_rent_psf": 28.4772
  },
  "formula": { "id": "calc.net_effective_rent", "version": 1 },
  "steps": [ … every intermediate value, with its formula … ],
  "warnings": []
}

3. A registry lookup comes back cited

Schematic example. This is the documented shape of a registry fact (method, source snapshot, record locator, rights); the owner name is a placeholder and the account number is the one used in the registry documentation.

{
  "subject": "fl:parcel:us-48201:0011440000001",
  "predicate": "ownership.owner_of_record",
  "value": "ACME PROPERTIES, L.L.C.",
  "as_of": "2026-07-25",
  "provenance": {
    "method": "public_record",
    "sources": [
      {
        "document_id": "fl:document:sha256-…",
        "title": "Harris Central Appraisal District: Appraisal roll (real_acct.zip)",
        "uri": "https://…",
        "retrieved_at": "2026-11-02T…",
        "section": "account 0011440000001"
      }
    ]
  },
  "rights": { "ai_use": "…", "redistribution": "…", "license": "public record" }
}

Three layers

Tools

What the calculators cover

26 deterministic calculators: rent schedules, net effective rent, proposal comparison, percentage rent, CAM reconciliation, debt sizing, ASC 842 remeasurement, prepayment and defeasance, WALT, NPV, IRR, lease vs. own, renew vs. relocate, hotel metrics, property DCF pro forma, direct cap, loan amortization, LP/GP equity waterfalls, 1031 exchange checks, multifamily rent rolls, capital expenditure recovery, building-wide CAM, lease critical dates, Texas unequal-appraisal comparisons, and tie-outs of a DCF or CAM reconciliation against your own model. Every result carries steps (the audit trail), warnings, and a versioned formula ID such as calc.net_effective_rent@1.

Stable FactLot IDs for parcels, legal entities, buildings (from the street address), spaces, and documents, computable offline; leases get IDs minted by a registry. A fact schema in which every claim carries its provenance (document, page, clause, method) and its AI-use rights.

Calculators · ID specification · Fact model

Registry

Parcel to owner of record to registered entity, from public records only. Every fact cites the public file it was read from, with the record locator, the publisher's licence, and its AI-use and redistribution status.

What else the pipeline holds, and what is not hosted

The pipeline also holds zoning, recorded sales, deeds and mortgages, energy benchmarks, CMBS loan data and 6,994 federal lease comps for the metros the coverage page lists. The hosted API also serves the 6,994 GSA lease comps (lease_comp_search; the federal government is the tenant, so they are not private-market comps). Tarrant County is not served by the hosted registry while the publisher's terms for AI use are unclear. Call registry_coverage first to see what is hosted. The other regions are built and verified in the project's pipeline and run on your own FactLot with a registry file; more hosted regions open as their terms allow.

Registry · Source catalog · Try it: DC sample (23.5 MB)

Rules and document verification

Rules packs turn jurisdiction law into code. Each pack cites its statute, carries a version, and stays draft until a maintainer has checked it against the official text; the pack records who checked it and when. One pack is verified today: the Texas property-tax protest deadline (checked 2026-11-02).

What document verification checks

Document verification checks what your agent reads from a lease. Your agent extracts each term with its verbatim quote and page; FactLot confirms the quote is on that page and states the value ("$1,250,000.00", "June 30, 2031", "five percent (5%)") and returns a cited fact, or the reason it could not. It also builds a current-state abstract with amendment precedence, compares an estoppel or rent roll to the lease, and checks a single claim. No model runs on our side, and the checks are textual: they do not find terms your agent missed. Live on the hosted API; nothing is stored. It also spreads a T-12 onto a published chart of accounts with every line cited, checks a proposed use against a center's exclusives, and packages verified facts so a counterparty can check them, signed with your own key.

Rules packs · Texas protest deadline · Lease ingestion · Document verification

Counties hosted

Map of the United States with the counties the hosted registry answers for marked. Open the full coverage map.
Texas: counties with hosted data Bell County, TX: Hosted lookups. 13,685 commercial parcels, data as of 2026-10-01. Brazos County, TX: Hosted lookups. 8,252 commercial parcels, data as of 2026-08-11. Cameron County, TX: Hosted lookups. 14,173 commercial parcels, data as of 2026-07-23. Collin County, TX: Hosted lookups. 18,035 commercial parcels, data as of 2026-11-02. Dallas County, TX: Hosted lookups. 59,645 commercial parcels, data as of 2026-10-12. Denton County, TX: Hosted lookups. 13,304 commercial parcels, data as of 2026-11-07. Ector County, TX: Hosted lookups. 7,036 commercial parcels, data as of 2026-07-22. Galveston County, TX: Hosted lookups. 10,088 commercial parcels, data as of 2026-08-05. Grayson County, TX: Hosted lookups. 6,613 commercial parcels, data as of 2026-10-15. Guadalupe County, TX: Hosted lookups. 4,081 commercial parcels, data as of 2026-07-28. Harris County, TX: Hosted lookups. 87,717 commercial parcels, data as of 2026-11-01. Jefferson County, TX: Hosted lookups. 9,594 commercial parcels, data as of 2026-10-07. Johnson County, TX: Hosted lookups. 4,416 commercial parcels, data as of 2026-08-10. Kaufman County, TX: Hosted lookups. 3,557 commercial parcels, data as of 2026-07-17. Midland County, TX: Hosted lookups. 7,641 commercial parcels, data as of 2026-08-17. Nueces County, TX: Hosted lookups. 13,634 commercial parcels, data as of 2026-10-13. Travis County, TX: Hosted lookups. 30,556 commercial parcels, data as of 2026-10-06. Williamson County, TX: Hosted lookups. 11,758 commercial parcels, data as of 2026-11-07. Harris Dallas Travis Cameron Nueces Jefferson Brazos Midland Ector

Texas

Maryland to Boston: counties with hosted data District of Columbia, DC: Hosted lookups. 18,077 commercial parcels, data as of 2026-11-04. Allegany County, MD: Hosted lookups. 3,434 commercial parcels, data as of 2026-11-05. Anne Arundel County, MD: Hosted lookups. 9,049 commercial parcels, data as of 2026-11-05. Baltimore County, MD: Hosted lookups. 14,490 commercial parcels, data as of 2026-11-05. Calvert County, MD: Hosted lookups. 1,042 commercial parcels, data as of 2026-11-05. Caroline County, MD: Hosted lookups. 887 commercial parcels, data as of 2026-11-05. Carroll County, MD: Hosted lookups. 3,327 commercial parcels, data as of 2026-11-05. Cecil County, MD: Hosted lookups. 2,606 commercial parcels, data as of 2026-11-05. Charles County, MD: Hosted lookups. 3,043 commercial parcels, data as of 2026-11-05. Dorchester County, MD: Hosted lookups. 1,132 commercial parcels, data as of 2026-11-05. Frederick County, MD: Hosted lookups. 4,351 commercial parcels, data as of 2026-11-05. Garrett County, MD: Hosted lookups. 1,445 commercial parcels, data as of 2026-11-05. Harford County, MD: Hosted lookups. 3,738 commercial parcels, data as of 2026-11-05. Howard County, MD: Hosted lookups. 4,225 commercial parcels, data as of 2026-11-05. Kent County, MD: Hosted lookups. 677 commercial parcels, data as of 2026-11-05. Montgomery County, MD: Hosted lookups. 11,579 commercial parcels, data as of 2026-11-05. Prince George's County, MD: Hosted lookups. 13,029 commercial parcels, data as of 2026-11-05. Queen Anne's County, MD: Hosted lookups. 1,530 commercial parcels, data as of 2026-11-05. St. Mary's County, MD: Hosted lookups. 1,944 commercial parcels, data as of 2026-11-05. Somerset County, MD: Hosted lookups. 995 commercial parcels, data as of 2026-11-05. Talbot County, MD: Hosted lookups. 1,416 commercial parcels, data as of 2026-11-05. Washington County, MD: Hosted lookups. 3,716 commercial parcels, data as of 2026-11-05. Wicomico County, MD: Hosted lookups. 3,201 commercial parcels, data as of 2026-11-05. Worcester County, MD: Hosted lookups. 3,592 commercial parcels, data as of 2026-11-05. Baltimore city, MD: Hosted lookups. 14,801 commercial parcels, data as of 2026-11-05. Suffolk County, MA: Hosted lookups for the City of Boston only. 13,296 commercial parcels, data as of 2025-01-01. Bronx County, NY: Hosted lookups. 17,331 commercial parcels, data as of 2026-09-30. Kings County, NY: Hosted lookups. 60,100 commercial parcels, data as of 2026-09-30. New York County, NY: Hosted lookups. 42,087 commercial parcels, data as of 2026-09-30. Queens County, NY: Hosted lookups. 40,080 commercial parcels, data as of 2026-09-30. Richmond County, NY: Hosted lookups. 5,035 commercial parcels, data as of 2026-09-30. Allegheny County, PA: Hosted lookups. 35,302 commercial parcels, data as of 2026-11-02. Fairfield County, CT: Hosted lookups. 8,607 commercial parcels, data as of 2026-11-09. Hartford County, CT: Hosted lookups. 11,567 commercial parcels, data as of 2026-11-09. Litchfield County, CT: Hosted lookups. 3,280 commercial parcels, data as of 2026-11-09. Middlesex County, CT: Hosted lookups. 2,465 commercial parcels, data as of 2026-11-09. New Haven County, CT: Hosted lookups. 11,284 commercial parcels, data as of 2026-11-09. New London County, CT: Hosted lookups. 2,962 commercial parcels, data as of 2026-11-09. Tolland County, CT: Hosted lookups. 1,451 commercial parcels, data as of 2026-11-09. Windham County, CT: Hosted lookups. 1,782 commercial parcels, data as of 2026-11-09. District of Columbia Maryland New York City Connecticut Boston

Maryland to Boston

Utah, Denver and California: counties with hosted data Beaver County, UT: Hosted lookups. 168 commercial parcels, data as of 2025-10-23. Cache County, UT: Hosted lookups. 2,092 commercial parcels, data as of 2026-10-13. Davis County, UT: Hosted lookups. 2,583 commercial parcels, data as of 2025-11-26. Duchesne County, UT: Hosted lookups. 546 commercial parcels, data as of 2025-10-23. Garfield County, UT: Hosted lookups. 188 commercial parcels, data as of 2025-10-23. Grand County, UT: Hosted lookups. 62 commercial parcels, data as of 2025-10-23. Juab County, UT: Hosted lookups. 359 commercial parcels, data as of 2025-11-26. Kane County, UT: Hosted lookups. 258 commercial parcels, data as of 2026-10-13. Millard County, UT: Hosted lookups. 368 commercial parcels, data as of 2025-10-23. Morgan County, UT: Hosted lookups. 160 commercial parcels, data as of 2026-10-05. Piute County, UT: Hosted lookups. 66 commercial parcels, data as of 2026-10-13. Rich County, UT: Hosted lookups. 281 commercial parcels, data as of 2026-10-13. Salt Lake County, UT: Hosted lookups. 30,756 commercial parcels, data as of 2026-09-29. Sevier County, UT: Hosted lookups. 582 commercial parcels, data as of 2025-10-23. Summit County, UT: Hosted lookups. 1,169 commercial parcels, data as of 2025-11-26. Tooele County, UT: Hosted lookups. 617 commercial parcels, data as of 2025-10-23. Uintah County, UT: Hosted lookups. 1,937 commercial parcels, data as of 2025-10-23. Utah County, UT: Hosted lookups. 13,639 commercial parcels, data as of 2026-09-30. Washington County, UT: Hosted lookups. 8,400 commercial parcels, data as of 2026-09-30. Wayne County, UT: Hosted lookups. 117 commercial parcels, data as of 2025-10-23. Weber County, UT: Hosted lookups. 3,629 commercial parcels, data as of 2026-09-29. Los Angeles County, CA: Hosted lookups. 203,179 commercial parcels, data as of 2026-10-14. Sacramento County, CA: Hosted lookups. 20,053 commercial parcels, data as of 2026-11-01. San Francisco County, CA: Hosted lookups. 19,048 commercial parcels, data as of 2026-06-26. Denver County, CO: Hosted lookups. 13,539 commercial parcels, data as of 2026-10-29. Juab Summit Denver Los Angeles San Francisco

Utah, Denver and California

Indiana and Michigan: counties with hosted data Marion County, IN: Hosted lookups. 20,626 commercial parcels, data as of 2026-11-09. Oakland County, MI: Hosted lookups. 26,122 commercial parcels, data as of 2026-11-09. Marion Oakland

Indiana and Michigan

Georgia and North Carolina: counties with hosted data DeKalb County, GA: Hosted lookups. 11,357 commercial parcels, data as of 2026-11-09. Wake County, NC: Hosted lookups. 9,634 commercial parcels, data as of 2026-05-17. DeKalb Wake

Georgia and North Carolina

Hosted: Maryland (all 24 jurisdictions), the District of Columbia, 21 counties in Utah, eighteen Texas counties (Harris, Dallas, Travis, Collin, Cameron, Bell, Nueces, Denton, Williamson, Galveston, Jefferson, Brazos, Midland, Ector, Grayson, Johnson, Guadalupe and Kaufman), New York City (all five boroughs), Los Angeles County, San Francisco, the City of Boston, Denver, Connecticut (statewide, by town), Sacramento County (CA), DeKalb County (GA), Marion County (IN), Oakland County (MI), Wake County (NC), and Allegheny County (PA). Commercial, industrial, and multifamily parcels only; some public files omit owner names.

The open-source registry pipeline has also built counties the hosted API does not serve; they run on a self-hosted FactLot with a registry file. The coverage map shows both, county by county.

Connect

Every platform serves the same tools, generated from one catalog, so a calculation returns the identical answer, steps, and formula ID wherever it was called from.

Custom connector (remote MCP), one-click Desktop extension, Claude Code plugin with twelve CRE skills (/plugin marketplace add 9mp96ygnbk-alt/factlot), Claude API

Claude guide

claude.ai, Claude Desktop and mobile: custom connector

https://api.factlot.com/mcp/signin

Claude Code

claude mcp add --transport http factlot https://api.factlot.com/mcp

Claude Desktop: extension file (local)

https://github.com/9mp96ygnbk-alt/factlot/releases/download/v0.5.0/factlot-0.5.0.mcpb

ChatGPT app (developer mode, deep research), Custom GPT Action, Responses API remote MCP, function calling

ChatGPT guide

ChatGPT: app by URL (developer mode)

https://api.factlot.com/mcp/signin

Custom GPT Action (OpenAPI)

https://api.factlot.com/openapi-3.0.json

OpenAI Responses API: remote MCP

from openai import OpenAI

client = OpenAI()
response = client.responses.create(
    model=MODEL,
    tools=[{"type": "mcp", "server_label": "factlot", "server_url": "https://api.factlot.com/mcp", "require_approval": "never"}],
    input="Compare these two office proposals for my client: ...",
)

Gemini API function calling, Gemini CLI over MCP, Vertex AI

Gemini guide

Gemini CLI

gemini mcp add --transport http factlot https://api.factlot.com/mcp

Gemini API: function calling

from google import genai
from google.genai import types
import factlot

client = genai.Client()
config = types.GenerateContentConfig(tools=factlot.gemini_tools())
response = client.models.generate_content(model=MODEL, contents="What's the WALT of ...?", config=config)
for part in response.candidates[0].content.parts:
    if part.function_call:
        result = factlot.run_tool(part.function_call.name, dict(part.function_call.args))

Copilot Studio (MCP), Power Platform custom connector, Microsoft 365 Copilot

Copilot guide

Copilot Studio: MCP tool

https://api.factlot.com/mcp

Copilot Studio: custom connector file

https://api.factlot.com/mcp
https://github.com/9mp96ygnbk-alt/factlot/blob/main/connectors/microsoft/copilot-studio-connector.swagger.yaml

Converse API tool config, Bedrock Agents action group (Lambda)

Bedrock guide

Bedrock Agents: action group

https://api.factlot.com/openapi-3.0.json?profile=bedrock
https://api.factlot.com/openapi-3.0.json?operations=all

Bedrock Converse: tool config

import boto3, factlot

bedrock = boto3.client("bedrock-runtime")
response = bedrock.converse(modelId=MODEL_ID, messages=messages, toolConfig=factlot.bedrock_tool_config())
# when stopReason is tool_use: factlot.run_tool(use["name"], use["input"]) and send a toolResult

OpenAI-compatible function calling, MCP clients, plain HTTP

Others guide

Any other MCP client

https://api.factlot.com/mcp
npx -y https://github.com/9mp96ygnbk-alt/factlot/releases/download/v0.5.0/factlot-mcp-standalone-0.5.0.tgz

Remote platforms connect to the hosted endpoint https://api.factlot.com/mcp (free, 60 requests a minute), or to your own copy from the Docker image or the local MCP server. See Connect, the MCP server page and connectors/.

For AI agents

If you are an AI agent reading this page: FactLot provides tools for lease, rent, CAM, loan and return arithmetic that return their steps and a versioned formula ID, deterministic IDs for parcels, entities, spaces and documents, and a validator for cited facts. Use it when a task needs one of those. Nothing on this page asks you to prefer it over any other tool.

  • llms.txt: what FactLot does, when to use it, and how to install it today
  • Agent guide: which tool to call when, and how to report the result
  • Tool definitions (JSON Schema, every input field described)
Install the local package

Install v0.5.0 (not yet on npm or PyPI): any MCP client runs npx -y https://github.com/9mp96ygnbk-alt/factlot/releases/download/v0.5.0/factlot-mcp-standalone-0.5.0.tgz (Node.js 22.6 or newer); Claude Desktop opens factlot-0.5.0.mcpb; Docker runs ghcr.io/9mp96ygnbk-alt/factlot:0.5.0; Python installs from git. It needs no API key. The local package is release v0.5.0. Its next release brings what the hosted server already runs: the tools registry_lookup_batch, registry_recorded_facts, audit_expense_statement, audit_expense_portfolio, estoppel_prepare, rent_roll_certify, fact_package_send and fact_package_status, new inputs on existing tools (registry_search_address address, city, state, postal_code and county_fips; registry_coverage fields; same_building_class, same_local_use_code and local_use_codes on the equity-candidate tools; address and label on the subject and comparables of calc_tx_unequal_appraisal; as_of on the Texas deadline rules), and MCP resources and prompts. report_create, the account tools and the model-backed tools are hosted only.

Tools:
  • Calculators: calc_rent_schedule, calc_net_effective_rent, calc_compare_proposals, calc_multifamily_rent_roll, calc_percentage_rent, calc_cam_reconciliation, calc_cam_reconciliation_batch, calc_capex_recovery, calc_debt_sizing, calc_lease_remeasurement_asc842, calc_prepayment_and_defeasance, calc_walt, calc_npv, calc_irr, calc_lease_vs_own, calc_renew_vs_relocate, calc_hotel_metrics, calc_dcf_pro_forma, calc_direct_cap, calc_amortization_schedule, calc_equity_waterfall, calc_exchange_1031, calc_critical_dates, calc_reconcile_dcf, calc_reconcile_cam, calc_tx_unequal_appraisal
  • Rules: rules_tx_property_tax_protest_deadline, rules_tx_property_tax_protest_deadline_batch
  • IDs and facts: id_parcel, id_entity, id_space, id_building, id_document, id_parse, fact_validate, fact_package_create, fact_package_verify, lease_comp_validate, lease_comp_search
  • Documents: doc_verify_facts, doc_abstract_lease, doc_compare, doc_verify_claim, doc_spread_statement, doc_check_use_conflict, doc_predicates
  • Reports (hosted only): report_create builds an XLSX, PDF or ICS file from a tool result, by code with no model
  • Discovery: search, fetch, schema_get
  • Registry: eleven registry_* lookups, hosted for the regions registry_coverage lists and available on a self-hosted FactLot with a registry file

Pricing

The tools are open source and free to run yourself, with no limits. The hosted endpoint at https://api.factlot.com saves you running it.

Free

$0, no key needed

  • Every calculator, ID, fact, rules and document tool
  • 60 requests a minute per IP address
  • 25 registry lookups a day per IP address
  • 3 reports a month per IP address
  • Optional free key by email: requests and lookups on its own meter

Get started

Team

$599 a month

  • Up to 5 API keys
  • 3,000 requests a minute
  • 100,000 registry lookups a month
  • 1,000 reports a month
  • Priority support
  • A vote on which regions open next

Start Team

$599 a month, renews monthly until cancelled. Cancel any time. Terms

Enterprise

By quote

  • Enterprise: private deployment and invoicing, by quote. A signed data-processing agreement and SSO are not available yet

Email contact@factlot.com

Eight things on the hosted API need a Pro or Team key

Plans also differ in request rate, registry lookups, reports, keys and support. Full comparison.

Quotas, checkout and cancelling

How quotas work. Limits are hard caps with no overage charges. Free registry lookups count per IP address per day; paid lookups count per subscription per month, shared by a plan's keys. A lookup is one call to a registry_* tool that finds something: a record, a resolved ID, owners or search results. Not counted: a call that finds nothing (an empty list, urn null or a NotFound inside loaded coverage; up to an hourly limit), registry_coverage, input errors, misses outside loaded coverage (county, state, entity registry or ID system not loaded) and calls the registry could not answer. Days and months are UTC. At a cap the call returns HTTP 429 with the reset time and a link to this page. Calculator, ID, fact, rules and document tools never count toward a lookup quota.

Checkout is by Stripe; prices are in US dollars and exclude taxes. Your API key is shown once on the page Stripe returns you to; FactLot stores only a hash of it, and a new key can take up to a minute to start working. Cancel any time at factlot.com/account, in the Stripe billing portal, or by email to contact@factlot.com with the subject "Cancel" from your account email; your key works to the end of the period you have paid for (a month, or a year on Pro yearly), and there are no refunds for a partial period except as the terms say. Agents can start checkout with POST https://api.factlot.com/v1/billing/checkout, hand the link to their human, and collect the key from the claim_url it returns. See the terms and the privacy notice.

Regions not hosted yet

Need a region that is not hosted yet? Email contact@factlot.com with your company, use case, metros, and lookups per month, or ask in GitHub Discussions. Please do not send confidential leases or personal data by email.

Open source

Every tool is open source and self-hostable, which matters when leases are confidential. The hosted endpoint runs the same code.

Source · Contributing · Security · Changelog

  • Schema and SDKs: @factlot/schema, @factlot/tools and the client SDKs. MIT.
  • Platform: calculators, IDs, rules, the MCP server, the remote connector, and the ingest and registry code. Apache-2.0.
  • Hosted: https://api.factlot.com, free at 60 requests a minute, with paid plans for higher limits. Registry lookups are on every plan: 25 a day free, 5,000 a month on Pro, 100,000 a month on Team.

Principles

  • Public records only, obtained ethically. Official bulk downloads, open-data portals, public APIs within their terms, or a records request. No circumventing access controls, no scraping where terms forbid it, no data whose licence forbids redistribution or AI use.
  • Organisations, not people. The registry keeps commercial parcels and the organisations that own them. It is built to exclude natural persons' names, and withheld owner records are never recovered or inferred. If a record names you as a person, or is wrong, email contact@factlot.com and we will remove or correct it.
  • Everything cited. Uncited facts are rejected: extracted, public-record and inferred facts must name a source, and computed facts their formula. Each fact names its method, its source document and record, and the rights that travel with it.
  • Deterministic. The TypeScript and Python SDKs produce the same result, checked by shared test vectors and a differential test that fails on any difference, down to the last digit.