Lotmark turns parcel, hazard, terrain, building, and environmental data into structured, source-cited features — built for the AI products being built in proptech, insurance, and mortgage today.
Agent workflows: Connect via MCP · source-cited parcel tools
GET /v1/parcels/lm_ca_079-020-011 · response snapshot{ "parcel_id": "lm_ca_079-020-011", "freshness_days": 2, "parcel": { "apn": "079-020-011", "address": "10275 Loch Haven Dr, Santa Rosa, CA", "land_acres": 1.02, "source": { "agency": "County of Sonoma", "product": "Parcels Public", "accessed": "2026-07-24", "record_count": 189239 } }, "risk_features": { "fire": { "fhsz_zone": "High", "responsibility_area": "SRA", "wildfire_hazard_potential_class": "high", "wildfire_hazard_potential_value": 4, "distance_to_burn_perimeter_m": 0, "nearest_burn_name": "C. HANLY", "last_burn_year_within_5km": 2019, "years_since_last_fire": 7, "source": { "agency": "CAL FIRE", "product": "FHSZ SRA 2024 point intersect", "accessed": "2026-07-24" }, "confidence": 0.9 }, "flood": { "fema_zone": "X", "in_sfha": false, "source": { "agency": "FEMA NFHL", "panel_id": "06097C0735F" } } }, "building": { "primary_year_built": 1979, "primary_size_sqft": 2839, "source": { "agency": "County of Sonoma", "product": "Parcels Public", "as_of": "2026-05-02" } }, "terrain": { "elevation_ft": 583.9, "local_relief_150m_ft": 153.66, "slope_degrees": 6.7, "aspect_degrees": 157.7, "source": { "agency": "USGS", "product": "3DEP 30m raster sample" } }, "soil": { "mukey": "459807", "mapunit_name": "Laniger loam, 15 to 30 percent slopes", "hydrologic_group": "C", "drainage_class": "Well drained", "source": { "agency": "USDA NRCS", "product": "SSURGO/SDA" } }, "vegetation": { "canopy": { "canopy_percent": 29, "year": 2023, "source": { "agency": "USDA Forest Service", "product": "NLCD Tree Canopy Cover 2023" } } }, "narrative": { "text": "1.02 acre parcel, in High fire hazard zone, with a 1979 primary structure, at 583.9 ft elevation.", "grounded_in": ["parcel", "building", "terrain", "risk.fire", "risk.flood"] }, "embedding": { "dim": 1536, "model": "text-embedding-3-small", "status": "metadata_only" } }
Every field carries a source object with agency, product, and date. Narratives ship with a grounded_in array so your RAG pipeline can verify them. Embeddings included.
County parcel, hazard, terrain, soil, canopy, and building sources normalized to a single parcel schema, enriched with LLM narratives and embeddings, and exposed through one API. Each step is auditable; each output is cited.
County assessor parcels and building attributes, USGS 3DEP terrain, FEMA NFHL, USFS WHP, CAL FIRE FHSZ and burn perimeters, USDA SSURGO, and NLCD tree canopy.
Geospatial joins, zonal stats, distance features, slope/elevation derivation, LLM-generated narratives, 1536-dim embeddings, quality gates.
REST endpoints. Tool-call-shaped JSON. Bulk download for Growth tier. Webhook refresh signals. Source provenance on every field.
Every datapoint ships with the agency, product version, and as-of date that produced it. Your RAG pipeline can verify claims. Your underwriters can defend them.
Distance to burn perimeter, WHP class, FHSZ zone, slope, canopy, soil — composable inputs your model can reason over. No black-box 1-10 number you can't audit.
Structured JSON, pre-generated narratives, included embeddings. Drop into your agent's tool definitions in minutes — not weeks of feature engineering.
Surface fire, flood, and roof signals at quote-time. Catch hazard mismatches before the binder issues.
Climate-exposed properties surface their risks at application, not at appraisal. Fewer surprises late in close.
Give your agent factual property data with citations instead of hallucinations from training data.
Slope, soil, flood, hazard, and distance features for development, solar siting, and portfolio risk.
Lotmark launches with four states where wildfire, flood, and wind exposure are reshaping property economics — and where the data is publicly available and rigorously source-able.
Give Claude or Codex read-only tools to discover parcel datasets, look up properties, inspect source citations and QA, and enrich a batch of parcels. Returned fields depend on the approved dataset and its source coverage.
MCP endpoint: https://api.lotmark.io/mcp
The MCP uses Authorization: Bearer with your existing customer API key on every request. No OAuth sign-in or local server package is required.
Already have a Lotmark API key? Use it here. Otherwise request a key through developer access or checkout. Keep credentials out of contact forms, shared configuration, URLs, and chat messages.
For Claude Code and Codex, set LOTMARK_API_KEY in the environment that launches the client. This Bash / zsh prompt hides your input and keeps the key out of shell history. Run it in your own terminal, then start the chosen client in that same terminal. A secret manager may supply the variable instead.
Enter your own key only at the hidden terminal prompt. This website never receives it. Environment variables last for that shell session.
Merge this server entry into your project's .mcp.json, preserving any existing servers. Claude Code expands the environment reference in the header. Launch claude from the shell holding your key, approve the project server if prompted, and use /mcp to inspect status and tools.
Select and copy this text manually, or use the copy button. Configuration contains environment references, never your key.
With the Codex CLI installed, register the server below. The token flag stores the environment-variable name, not the key. Launch codex from the shell holding your key; use /mcp to inspect active servers.
Select and copy this text manually, or use the copy button. Configuration contains environment references, never your key.
Merge into ~/.codex/config.toml, or a trusted project's .codex/config.toml. Desktop/IDE clients must receive LOTMARK_API_KEY in their launch environment too; restart after configuring it.
Select and copy this text manually, or use the copy button. Configuration contains environment references, never your key.
This uses your Claude account’s remote connector settings, separately from Claude Code. It requires an HTTPS endpoint reachable from Anthropic’s cloud. Use the endpoint shown above.
Authorization and privately enter Bearer followed by your own Lotmark key. Environment references are for CLI clients; enter the real value only in Claude’s private credential setting.On Team/Enterprise, a fixed connector credential is shared by its users. Use an organization-approved key with appropriate access. Local Desktop claude_desktop_config.json is a separate mechanism; this HTTP server has no local stdio launcher.
These instructions match the server’s HTTP and bearer-key contract. Client connection verification is separate: copying or saving configuration does not prove initialization, tool discovery, or a successful parcel lookup.
Priced by successful parcel enrichment, not generic API calls. Every included unit returns structured features, citations, narratives, and embeddings.
For testing the API shape before production.
Request accessFor solo founders and AI prototypes.
Start BuilderFor production apps and small teams.
Start StartupFor scaling teams in proptech, insurance, mortgage.
Start GrowthEnterprise starts at $3k-$10k+/mo for annual contracts, redistribution rights, SLAs, and custom coverage. Talk to us about Enterprise.
Public methodology, open dataset cards, no resold feeds.
For instant API access, grab a key from pricing above. Use this form for Enterprise, developer access, demo bookings, or anything else.