location-risk-mcp
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@location-risk-mcp Pre-screen 1700 District Ave, Burlington, MA for a homeowners policy"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
location-risk-mcp
Independent prototype, not a Precisely product and not affiliated with Precisely. Built by Pranav Yadav as a personal project. It calls Precisely's hosted MCP server with the user's own trial credentials. Decision support only: it does not make or recommend underwriting decisions.
An MCP server that gives an AI agent what it needs to pre-screen a property for a homeowners policy. It provides three tools, each shaped around a step in the agent's task:
standardise_address ──► enrich_location ──► summarise_risk_context
messy text in flood, wildfire, overall level, flags ranked
one location_id out quake, crime, fire by severity, evidence for
(or candidates/none) station, building each flag, follow-ups, gapsIn live mode it is a task layer on top of Precisely's hosted MCP server. Precisely exposes its data services as hundreds of actions behind three generic tools (precisely_actions_search / _describe / _execute). That's ideal for discovery, but an agent running an underwriting pre-screen would have to find, sequence and interpret seven actions every time. This server does that once, deterministically:
Step | Precisely actions used |
|
|
|
|
| none: versioned rules over the enrichment ( |
Why it is shaped this way
Task-shaped tools, not endpoint wrappers. The agent passes a
location_idfrom step to step. It never carries coordinates or IDs between calls, and never has to know which of Precisely's actions holds which field.Every value is citable. Outputs are typed (each tool publishes an MCP
outputSchema). Each data block carries its ownsource:data_source(fixtureorlive), the Precisely action it came from,retrieved_atand the datasetvintage. Each risk flag lists the exact fields it rests on.Gaps are reported, never filled. Provider placeholders (
-9999, empty{value: null}objects, a crime index of0with no category) become gaps, not numbers. One failing action becomes a gap for that block only. If a core peril (flood or wildfire) can't be assessed, the summary saysinsufficient_datainstead oflow.Corrections are surfaced. If the geocoder changed something the user typed (e.g. a different ZIP),
standardise_addressreturns a warning to confirm with the applicant.Ambiguity goes back to the user. Close-scoring candidates return
status: ambiguous, and the server instructions tell the agent to ask, not pick.Data minimisation.
property.attributesalso returns owner names, tax mailing addresses and sale history. None of that is passed to the agent; only building attributes are.The risk rules are deterministic and versioned. The same input always gives the same summary, so it can be tested and audited.
Read-only by declaration. All tools set
readOnlyHintandidempotentHint.openWorldHintis true only in live mode.
Related MCP server: PropertyScoop MCP Server
Quick start (fixture mode, no account needed)
python3 -m venv .venv
.venv/bin/pip install -e ".[dev]"
.venv/bin/python -m pytest -q # 24 tests, no network
.venv/bin/python scripts/demo.py # full flow through a real MCP client over stdioFixture mode serves bundled synthetic data (src/location_risk_mcp/fixtures/locations.json). Every address and value in it is invented, and every response is stamped data_source: "fixture".
Live mode (your own Precisely trial)
Create
.envfrom the template, then add the API key and secret from your Precisely workspace..envis git-ignored.cp .env.example .envSet
PRECISELY_MODE=live. The server authenticates tohttps://api.cloud.precisely.com/mcp(us-east-1; setPRECISELY_MCP_URLfor other regions) with the header Precisely documents:Authorization: Apikey base64(key:secret).Check the connection and run one address end to end:
.venv/bin/python scripts/doctor.py --probe "1700 District Ave, Burlington, MA 01803"Record a live transcript:
.venv/bin/python scripts/demo.py "<test address>" ...
Use test or sample addresses only, never real customer data.
Web UI (for demos)
.venv/bin/python -m location_risk_mcp.web # then open http://127.0.0.1:8765A single page: pick a country, enter an address, watch the three tool calls run with timings, and see the verdict, flags with their evidence chips, warnings, gaps and the raw MCP outputs. The page is just another MCP client: it calls the same three tools an agent would, so it shows exactly what an agent gets. It follows PRECISELY_MODE from .env, shows a FIXTURE or LIVE badge, and listens on localhost only.
Connect it to an MCP client
Claude Code:
claude mcp add location-risk -- /ABSOLUTE/PATH/location-risk-mcp/.venv/bin/python -m location_risk_mcp.serverClaude Desktop (claude_desktop_config.json):
{
"mcpServers": {
"location-risk": {
"command": "/ABSOLUTE/PATH/location-risk-mcp/.venv/bin/python",
"args": ["-m", "location_risk_mcp.server"]
}
}
}The server reads .env from the project folder. It also exposes an underwriting_prescreen prompt and, in fixture mode, a fixtures://sample-addresses resource. A matching Claude Skill is in skills/underwriting-prescreen.
Demo transcript (live mode)
Recorded on 2026-11-01 against Precisely's hosted MCP server, using addresses from Precisely's own documentation examples. Full transcript: demo/transcript.live.md. A synthetic-data run is in demo/transcript.fixture.md.
1700 District Ave, Burlington, MA 01803 → 1700 DISTRICT AVE, BURLINGTON, MA 01803 (building-level point, score 100)
overall moderate
MODERATE flood: zone X, but 204 ft from a 100-year flood zone. Evidence:
flood.zone='X',flood.distance_to_100yr_zone_ft=204. Next: check site elevation relative to the nearby flood zone. A zone-only check would have called this low.wildfire (Minimal), earthquake (site class C), fire response (1.55 road miles, about 10.6 min) and building age (1979): low.
Gaps (reported, not filled):
crime.composite_index(not populated for this block),earthquake.nearest_fault_miles.
2755 Milwaukee St, Denver, CO 80238 → 2755 N MILWAUKEE ST, DENVER, CO 80205 (score 86)
⚠ ZIP corrected: input 80238, matched 80205
overall elevated
ELEVATED theft_and_crime: crime index 174. MODERATE earthquake: nearest fault 12.75 mi. MODERATE building_age: built 1927.
Near the old mill → no_match: the agent stops and says so.
Layout
src/location_risk_mcp/
server.py MCP server: tools, prompt, resource, agent instructions
web.py, static/index.html local demo UI (an MCP client of server.py)
risk.py deterministic, versioned risk rules
models.py typed outputs (become each tool's outputSchema)
config.py settings from env/.env; never exposes secrets
providers/precisely_mcp.py client of the hosted Precisely MCP server + response mapping
providers/fixture.py synthetic data, no network
fixtures/locations.json
skills/underwriting-prescreen/SKILL.md
scripts/demo.py end-to-end run through a stdio MCP client
scripts/doctor.py config + connection check, live probe, action search
tests/ server (via MCP client), rules, live mapping (canned responses)Limits
Risk thresholds are illustrative, not any insurer's underwriting guidelines.
Risk context is US-only: every Precisely risk and property action used here covers US addresses only. Other countries (e.g.
IND) are standardised and geocoded live, and the risk blocks are skipped and reported as gaps, so the verdict isinsufficient_data, never a guess.One MCP session per tool call; a hosted version would keep a pooled session, a shared cache keyed by
location_id, and per-tenant auth on its own endpoint.Precisely's hosted MCP server is in Preview, so action names and response shapes may change. The mapping turns anything unexpected into gaps, and
doctor.py --probeshows them.
License
MIT. See LICENSE.
Available Tools
3 toolsenrich_locationEnrich locationBRead-onlyIdempotent
Hazard and property context for a standardised location: flood zone and distance to the 100-year zone, wildfire band, earthquake exposure, crime index, fire station drive distance, and building attributes (no owner or sale data).
Each block has its own source. Anything unavailable is listed in gaps, never estimated.
Inputs: location_id (required). Returns: gaps, crime, flood, property, +5 more
standardise_addressStandardise addressARead-onlyIdempotent
Turn a free-text address into one standardised, geocoded location with a location_id.
country is an ISO 3166 alpha-3 code (USA, IND, GBR, ...). Returns status 'matched' (use location.location_id next), 'ambiguous' (ask the user to choose from candidates) or 'no_match'. Missing components are listed in gaps. Risk enrichment covers US addresses only; elsewhere the risk blocks come back as gaps.
Inputs: address (required), country. Returns: gaps, input, status, location, +3 more
summarise_risk_contextSummarise risk contextARead-onlyIdempotent
Rule-based pre-screen summary: an overall level, flags ranked by severity with the evidence each one rests on, suggested follow-up questions, and data gaps.
Calls enrich_location itself if needed. Decision support only, not an underwriting decision.
Inputs: location_id (required), line_of_business. Returns: gaps, flags, disclaimer, location_id, +6 more
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 3 tools
The three tools form a strict sequential pipeline (standardise → enrich → summarise) and each targets a distinct stage with clearly different outputs: a location_id, hazard blocks, and a decision-support summary. Descriptions explicitly state the handoff (e.g. 'use location.location_id next', 'calls enrich_location itself if needed'), so there is no realistic misselection.
All three names follow the same verb_noun convention (standardise_address, enrich_location, summarise_risk_context) with consistent British spelling and snake_case. The pattern is fully predictable and readable.
Three tools is on the lean side, but each is a substantial, broad operation covering many sub-capabilities (geocoding, hazards, summarisation), so nothing feels redundant or missing. A single-address-at-a-time surface is a reasonable scope, though one extra tool (e.g. batch or lookup-by-id) could round it out.
The full lifecycle from free-text address to risk pre-screen is covered end-to-end, including ambiguity handling, gap reporting, and an internal enrich call. Minor gaps exist: no batch/multi-address processing, no standalone retrieval of a stored location or risk record by location_id, and no way to inspect available data sources or coverage beyond per-result gaps.
Related MCP Connectors
Flood, wildfire, earthquake, and coastal-storm hazard lookup for a US property.
US property risk data for agents: flood, hazards, taxes, air quality. Credits or USDC.
Household financial risk intelligence for financial advisors: coverage gaps and property exposure.
Read-only discovery for AddressRiskReport, a property risk report service for US homebuyers.
Related MCP Servers
- AlicenseAqualityCmaintenanceInstant U.S. property intelligence for AI agents. Zoning, Buildability™ Score, ADU eligibility, flood risk, and more from 20+ government sources. Pay-as-you-go: $5 per analysis (prepaid credits). Free Score available at buildability.us. Get a key at buildability.us/api.51MIT
- FlicenseNot gradedqualityDmaintenanceProperty intelligence API for US real estate. Returns 16+ data points for any US address: noise levels, wetlands, slope, natural light, powerline proximity, crime rates, property facing direction, zoning, public record, radon risk, natural hazards (earthquake, flood, wildfire), neighborhood demographics, falling tree risk, RF/cell tower exposure, and nearby school.-
- AlicenseNot gradedqualityDmaintenanceAssesses natural hazard exposure (flood, wildfire, earthquake, coastal proximity) for a single US property address using only free, keyless public data.MIT

perilpulseofficial
AlicenseNot gradedqualityCmaintenanceProvides per-property multi-peril risk scores (flood, wildfire, wind, hail, crime, etc.) for an address, returning A-F grades and 0-100 scores across 25+ hazard types for insurance underwriting and due diligence.83 npmMIT