# Health Insurance Coverage Source: https://docs.ihuus.com/api-reference/demographics/health-insurance-coverage /openapi.json get /demographics/insurance-coverage Sourced from the most recent US Census Bureau data. Measures the share of residents with any form of health insurance on a linear 0-255 scale. A score of 0 means no data is available or the local population count falls below the reporting threshold. A score of 1 represents near-zero coverage; 255 represents over 90% of residents insured. # Ideological Lean Score Source: https://docs.ihuus.com/api-reference/demographics/ideological-lean-score /openapi.json get /demographics/ideological-lean Derived from US Census Bureau data and voting records. The score runs from 1 (predominantly conservative) through 128 (evenly split) to 255 (predominantly liberal). A score of 0 means no data is available for the location. # Population Age Profile Source: https://docs.ihuus.com/api-reference/demographics/population-age-profile /openapi.json get /demographics/population-profile Derived from the most recent US Census Bureau data. Scores range from 1 (predominantly young adults aged 20-34, few children or seniors) to 255 (predominantly senior, strong 65+ population and high median age). 128 represents a balanced age mix across young adults, families, and older residents. A score of 0 means no data is available. # Air Quality Score Source: https://docs.ihuus.com/api-reference/environment/air-quality-score /openapi.json get /environment/air-quality Derived from OpenAQ monitoring station data. Scores range from 1 (consistently dangerous AQI readings — serious health risk for all residents) to 255 (consistently clean air with little to no health concern). A score of 0 means no monitoring data is available for the location. # Industrial Proximity Score Source: https://docs.ihuus.com/api-reference/environment/industrial-proximity-score /openapi.json get /environment/industrial-proximity Pro AI A composite metric combining overhead imagery analysis, EPA hazard data (including Superfund sites), and nearby business and industry POI density. Scores range from 1 (hazardous — active industrial sites or severe pollution indicators nearby) to 255 (exclusively residential — no warehouses, industrial facilities, or hazard sites detected). A score of 0 means no data is available for the location. # Noise Levels Score Source: https://docs.ihuus.com/api-reference/environment/noise-levels-score /openapi.json get /environment/noise-levels Quantifies acoustic comfort using federal noise modelling data for road, railroad, and aviation sources. The score is a serenity scale: 1 is the worst (extreme noise — immediate proximity to an airport runway or heavy rail) and 255 is the best (serene — nature sounds only). A score of 0 indicates no noise data is available, which typically implies a rural or very secluded location. The response includes the composite score and a human-readable breakdown of individual noise sources in decibels. # Fire Safety Score Source: https://docs.ihuus.com/api-reference/risk/fire-safety-score /openapi.json get /risk/fire Derived from CALFIRE State Responsibility Area (SRA) hazard severity zone designations. Currently available for California only. Higher scores indicate greater safety: 255 represents areas with no fire risk factors reported by CALFIRE; 1 represents Severe hazard zones requiring maximum protection measures. A score of 0 means no CALFIRE data is available, including all locations outside California. # Flood Safety Score Source: https://docs.ihuus.com/api-reference/risk/flood-safety-score /openapi.json get /risk/flood Derived from FEMA National Flood Hazard Layer (NFHL) designations. Higher scores indicate greater safety: 255 represents areas outside all mapped flood hazard zones (FEMA Zone C); 1 represents coastal high-hazard zones subject to wave action (FEMA V/VE), typically associated with elevated insurance costs. A score of 0 means no FEMA data is available for the location. # School Detail Source: https://docs.ihuus.com/api-reference/schools-&-ratings/school-detail /openapi.json get /schools/school/{nces_id} Returns full details for a single school identified by its 12-digit NCES ID, including contact information, enrollment figures, grade range, and rating. Use the school search or district search endpoints to obtain NCES IDs. # School Districts Source: https://docs.ihuus.com/api-reference/schools-&-ratings/school-districts /openapi.json get /schools/search/districts Returns the names and metadata of all school districts (Unified, Elementary, Secondary) that geographically overlap with the specified latitude and longitude. School district boundaries can overlap (e.g., an elementary district within a high school district). This data is provided by Federal NCES datasets. # Schools and Ratings Source: https://docs.ihuus.com/api-reference/schools-&-ratings/schools-and-ratings /openapi.json get /schools/search/school-ratings Returns the closest K-12 schools to the specified latitude and longitude, ordered by distance. Results include school name, level, district, rating (if available), and distance in meters. Data about schools and districts is provided by Federal NCES datasets. Sources for data ratings are provided in each school record. # Schools by District Source: https://docs.ihuus.com/api-reference/schools-&-ratings/schools-by-district /openapi.json get /schools/search/school-by-district Returns schools belonging to a specific school district, identified by its NCES Local Education Agency (LEA) identifier. Results are ordered alphabetically by school name. Use the districts endpoint to look up LEA identifiers for a given location. # Single Address Geocoding Source: https://docs.ihuus.com/api-reference/tools/single-address-geocoding /openapi.json get /tools/geocode-single Pro AI Converts an address into geographic coordinates. This endpoint takes a free-text location or address and returns the most likely latitude and longitude. It is designed specifically for Agentic usage where only a single definitive location is needed. To increase location accuracy, it is highly encouraged to provide as precise and complete an address as possible. Providing an optional two-letter country code (e.g., "us") is also strongly encouraged to increase accuracy. Returns null coordinates and an explanatory message if no results are found. # Dog Friendliness Score Source: https://docs.ihuus.com/api-reference/vibe/dog-friendliness-score /openapi.json get /vibe/dog-friendliness Pro AI Evaluates how suitable a neighborhood is for dog owners based on proximity to parks, trails, off-leash areas, and pet-friendly businesses. Scores range from 1 (High Traffic/No Space) to 255 (Dog Paradise). # Liveliness Score Source: https://docs.ihuus.com/api-reference/vibe/liveliness-score /openapi.json get /vibe/liveliness Pro AI Measures the activity level and density of social destinations in a neighborhood, derived from POI density, commercial mix, walkability, and urban character. Scores range from 1 (Quiet Enclave) to 255 (Urban Hotspot). A score of 0 indicates no data is available for the location. # Privacy Index Score Source: https://docs.ihuus.com/api-reference/vibe/privacy-index-score /openapi.json get /vibe/privacy Pro AI Evaluates how secluded and private a neighborhood feels based on housing density, lot sizes, tree cover, and street-level visibility. Scores range from 1 (High Density) to 255 (Estate Sprawl). # Tranquility Index Score Source: https://docs.ihuus.com/api-reference/vibe/tranquility-index-score /openapi.json get /vibe/urban-rural Classifies the environment from dense urban core to open and tranquil countryside using imagery and population analysis. Scores range from 1 (dense urban core - wall-to-wall pavement, no greenery) to 255 (rural — farms, forests, barely a building). A score of 0 indicates no data is available for the location. # Visual Appeal Score Source: https://docs.ihuus.com/api-reference/vibe/visual-appeal-score /openapi.json get /vibe/visual-appeal Pro AI Rates the aesthetic quality of a neighborhood based on architectural character, landscaping, street-level cleanliness, and overall visual harmony. Scores range from 1 (Distressed) to 255 (Exclusive/Estate). # Walkability Score Source: https://docs.ihuus.com/api-reference/vibe/walkability-score /openapi.json get /vibe/walkability Assesses how walkable a neighborhood is based on sidewalk coverage, intersection density, proximity to amenities, and pedestrian infrastructure. Scores range from 1 (Car Dependent) to 255 (Pedestrian Priority). # Data Sources & Methodology Source: https://docs.ihuus.com/data/index How iHuus aggregates, fuses, and synthesizes hundreds of authoritative datasets into simple, queryable neighborhood intelligence. The iHuus Neighborhood Intelligence API is built on a massive, continuously updated data pipeline. We aggregate, clean, and fuse hundreds of authoritative datasets — from federal hazard layers to raw satellite imagery — into simple, queryable API endpoints and semantic **0–255 indices**. NCES, TEA, CDE and state-level district data Spatial imagery, road networks, and POI density OpenAQ, DOT noise models, EPA hazard layers US Census Bureau and American Community Survey FEMA NFHL flood zones and CALFIRE fire hazard tiers Mapbox-powered geocoding for agentic workflows *** ## Schools & Ratings We provide comprehensive, location-based school data, district boundaries, and performance metrics by harmonizing federal and state-level datasets. Core administrative, enrollment, and demographic data for every public K-12 school in the United States. State-specific performance metrics and district boundaries from sources including the Texas Education Agency (TEA), California Department of Education (CDE), and Florida Department of Education (FLDOE). We maintain current and historical data releases, further enriched from public school websites and local aggregators for completeness. Both school and district records return ratings on a **1–10 scale**. District results also include a `rating_summary` (a plain-language description of the district's performance) and a `rating_year` (the vintage of the rating), so you always know exactly where a rating came from and how current it is. *** ## Vibe "Vibe" is fundamentally difficult to quantify. We solve this by fusing multiple geospatial and physical-world datasets to evaluate the lived experience of a neighborhood across six dimensions: **Privacy, Walkability, Visual Appeal, Dog Friendliness, Urban-Rural Character,** and **Liveliness**. High-resolution overhead imagery and road network topologies reveal physical neighborhood structure: tree canopy coverage, lot sizes, pavement density, and sidewalk continuity. We analyze the density and category mix of local businesses and amenities — parks, cafes, pet stores, transit stops — to map lifestyle accessibility and neighborhood character. Visual Appeal, Privacy, Dog Friendliness and Liveliness are Pro AI dimensions computed via algorithmic synthesis of imagery and POI data. Scores represent probabilistic estimates, not guaranteed physical conditions. *** ## Environment Our environmental dimensions are calculated using a complex fusion of sensory data, hazard reporting, and spatial intelligence. | Dimension | Primary Source | What We Measure | | ------------------------ | ------------------------------------------------------------ | -------------------------------------------------------------- | | **Air Quality** | OpenAQ monitoring network | Consistency and severity of AQI readings over time | | **Noise Levels** | US Dept. of Transportation (DOT) + live flight path modeling | Road, railroad, and aviation noise in decibels | | **Industrial Proximity** | EPA Superfund data, spatial imagery, commercial POIs | Proximity to heavy industry, warehouses, and pollution sources | Noise scores include a **per-source breakdown** in the response description — road, railroad, and aviation dB levels — so engineers can surface exactly what's driving discomfort. *** ## Demographics We leverage authoritative government data to provide block-group-level insights into the people who make up a neighborhood. Health Insurance Coverage and Population Age Profiles are derived strictly from the most recent Census Bureau releases and the American Community Survey (ACS). We responsibly model political lean by synthesizing Census demographics with aggregated historical voting records and precinct-level data. Scores run from 1 (conservative) to 255 (liberal), with 128 as an even split. *** ## Risk We surface critical natural hazard data to help users understand the environmental liabilities of a specific location. Our risk model coverage is actively expanding. Flood risk covers CA, TX, and FL. Fire risk (CALFIRE) remains California only. Derived directly from the **FEMA National Flood Hazard Layer (NFHL)**, covering coastal high-hazard zones (V/VE), 100-year (A/AE), and 500-year (X/B) floodplains nationwide. Sourced from **CALFIRE** State Responsibility Area (SRA) hazard severity zone designations. Currently available for California locations only. Scores range from Severe (1) to no risk reported (255). *** ## Tools: Geocoding Our `/tools/geocode-single` endpoint is powered by the **Mapbox Geocoding API**. It takes a free-text address or place name and returns a single, definitive lat/lon pair. It is strictly designed for **LLM and agentic workflows**: agents geocode an address once, then pass coordinates to our intelligence endpoints. # MCP Servers Integration Source: https://docs.ihuus.com/guides/mcp Connect iHuus Neighborhood Intelligence directly to your AI agents using the Model Context Protocol (MCP). Pro AI The iHuus API natively supports the **Model Context Protocol (MCP)**, letting you plug high-fidelity geospatial data directly into AI assistants. Your agents can pull verified neighborhood data during conversations without any custom parsing or data pipelines. ## Why MCP Over Grounding? Most teams default to RAG/grounding pipelines when connecting external data to LLMs. For neighborhood intelligence, MCP is a better fit for two key reasons: Grounding relies on embedding similarity to retrieve chunks, and a wrong chunk can surface a mismatched tax record, an outdated zoning law, or a neighboring parcel's data. MCP eliminates that risk: your agent calls a typed endpoint with explicit coordinates, and the response is a single, authoritative record with source attribution. No retrieval ambiguity. Grounding pipelines inject large context windows of retrieved documents into every LLM call, and most providers charge a premium for grounding tokens. iHuus MCP tool calls return compact, structured payloads (a score and a one-line description), adding minimal input tokens. No extra LLM API surcharges, no bloated context windows. *** ## Connection Details Our MCP servers use **Streaming HTTP (SSE)** for transport. You need two things to connect: 1. Your **API token** (issued on your [account dashboard](https://map.ihuus.com/account)). 2. The **server URLs** for the intelligence domains you want to enable. ### Available MCP Servers We split tools into topical servers so you can grant your AI access only to the data it needs. | Server | URL | Capabilities | | ---------------- | -------------------------------------------- | ---------------------------------------------------------------------------------------- | | **Schools** | `https://api.ihuus.com/v1/mcp/schools/` | K-12 school search, ratings, district boundaries and district ratings | | **Vibe** | `https://api.ihuus.com/v1/mcp/vibe/` | Privacy, walkability, visual appeal, dog friendliness, urban-rural character, liveliness | | **Environment** | `https://api.ihuus.com/v1/mcp/environment/` | Noise levels, air quality, industrial proximity | | **Demographics** | `https://api.ihuus.com/v1/mcp/demographics/` | Insurance coverage, ideological lean, population age profile | | **Risk** | `https://api.ihuus.com/v1/mcp/risk/` | Flood risk (FEMA), fire risk (CALFIRE) | | **Tools** | `https://api.ihuus.com/v1/mcp/tools/` | Address geocoding and other utility functions | ### The Tools Server Most intelligence endpoints require `lat`/`lon` coordinates, but users typically provide street addresses or city names. The **Tools** server includes a geocoding endpoint that converts free-text addresses into coordinates, enabling your agent to work with our APIs out of the box. By connecting the Tools server alongside any intelligence server, your agent can handle the full workflow autonomously: receive an address from the user, geocode it, then query the relevant intelligence dimensions, all without the user needing to provide coordinates. *** ## Pre-built Extensions Don't want to wire up MCP servers by hand? The **[ihuus/mcp](https://github.com/ihuus/mcp)** GitHub repository ships ready-to-use extensions for **Claude Desktop** and **Gemini CLI** — no backend code required. One-click `.mcpb` bundle. Download, open, paste your API key — all 18 tools available instantly. Per-domain or all-in-one extensions. Clone the repo and link with a single `gemini extensions link` command. ### Quick Install **Claude Desktop** — no clone needed: ```bash theme={null} # 1. Download the bundle and open it in Claude Desktop # https://github.com/ihuus/mcp/raw/main/claude/desktop/mcpb.mcpb # 2. Paste your iHuus API key when prompted — done. ``` **Gemini CLI** — clone and link: ```bash theme={null} git clone https://github.com/ihuus/mcp.git cd mcp export IHUUS_API_KEY=your_key_here # https://ihuus.com/pricing export GEMINI_API_KEY=your_key_here # https://aistudio.google.com/apikey gemini extensions link gemini/full gemini ``` ### Example Output The extensions include a `neighborhood-analyst` skill that produces structured, multi-domain reports. Here is a sample output for **250 Mariposa Ave, Mountain View, CA** generated by Claude Desktop: Sample neighborhood report for 250 Mariposa Ave, Mountain View, CA generated by Claude Desktop using iHuus tools > Full interactive report: > [static.ihuus.com/reports/neighborhood\_report\_250\_mariposa\_ave.html](https://static.ihuus.com/reports/neighborhood_report_250_mariposa_ave.html) *** ## Client Setup & Model Selection These endpoints work with any modern MCP-compatible client: **Open WebUI**, **Gemini Studio**, **GitHub Copilot**, **Claude Desktop**, or your own custom agent. **Model selection tip:** Our tools return highly structured, semantic descriptions, so fast "Lite" models (like **Gemini 3.1 Flash Lite** or **Claude Sonnet 4.6**) execute tool calls rapidly and pass data to users efficiently. Larger "Pro" or "Deep Thinking" models often overthink standard data lookups. *** ## System Prompt To get reliable results, constrain your agent's behavior. LLMs will often hallucinate dummy coordinates if a user asks a vague question like "How are the schools in Texas?" The system prompt below forces the AI to rely strictly on iHuus data and ask for precise locations when needed. ```text theme={null} You are a helpful, knowledgeable, and conversational AI assistant specializing in neighborhood analysis and educational landscapes. ## Capabilities and Boundaries **General Knowledge** - You may use internal knowledge to discuss general geographic topics, state policies, or historical context. - If you use internal knowledge to discuss neighborhood characteristics, you MUST explicitly state that this is general knowledge and should be verified. **Verified Data (Your Tools)** - Your tools provide access to VERIFIED knowledge from trustworthy government and authoritative data sources. Tool output includes source attribution when available; highlight this to the user. - Tools typically require coordinates. Use the geocoding tool to convert addresses, city names, or neighborhoods into latitude and longitude. Precise addresses produce higher-quality, block-level results. - If tools are available to answer a query, you MUST use them first. You CAN augment tool output with general knowledge, but clearly distinguish verified tool data from your own knowledge. ## Rules for Tool Usage 1. **Rely on Metadata:** Read each tool's description, schema, and parameter annotations to understand exactly what inputs are needed. Do not assume. 2. **Never Guess or Hallucinate:** If the user's request is too broad or lacks required parameters, do not fabricate inputs to force a tool call. 3. **Ask Follow-up Questions:** If the tool requires specific inputs the user hasn't provided, politely ask a clarifying question before proceeding. 4. **Geocode First:** When a user provides an address or place name, convert it to coordinates using the geocoding tool before calling intelligence endpoints. ## Tone Be empathetic, clear, and straightforward. Mirror the user's energy. Stay concise unless detail is needed. Refer to tools as "my data" or "verified data sources." ## Data Sources and Citations Tools may include a specific data source reference and vintage year. These are HIGHLY AUTHORITATIVE. When providing facts from your own knowledge (not tools), make it clear the information should be independently verified. ``` *** ## Testing Your Agent Once your MCP servers are connected and your system prompt is applied, run through this conversation to verify the agent calls tools correctly: **1. Vague opener** (agent should ask for a specific address, not hallucinate coordinates) > *"Hey, I'm moving to Mountain View, CA. How is it there?"* **2. Environment query** (geocodes first via Tools, then triggers Environment server) > *"I'll be living near 250 Mariposa Ave. Is it noisy?"* **3. Schools query** (triggers Schools server — districts lookup, then school search) > *"My kids are 10 and 15. How good are the schools around that address?"* **4. Vibe query** (triggers Vibe server) > *"Will I be able to hear my neighbors, and is there a good place to walk my dog > nearby?"* **5. Risk query** (triggers Risk server) > *"Are there any flood or fire risks I should know about?"* **6. Full neighborhood report** (triggers all servers in parallel after geocoding — the best way to stress-test the full pipeline) > *"Give me a complete neighborhood report for 250 Mariposa Ave, Mountain View, CA."* A well-configured agent should geocode the address once, then call all domain tools in parallel and return a structured report covering Vibe & Character, Environment, Demographics, Risk, and Schools. # iHuus Neighborhood Intelligence Source: https://docs.ihuus.com/index High-performance data context layer for the AI era. **Early Access:** iHuus currently covers **California**, **Texas**, and **Florida**. We are actively expanding to more states: check back regularly for coverage updates. Building a chat interface is easy, but grounding it in physical reality is hard. Neighborhood data is scattered across petabytes of satellite imagery, noise rasters, and disjointed civic records. Feeding raw, unstructured civic data into LLMs inevitably leads to hallucinations and trust issues, especially when navigating strict Fair Housing Act (FHA) laws. **iHuus bridges the gap between raw physical-world data and agent-ready intelligence.** We process, normalize, and synthesize complex geospatial data into a proprietary architecture built specifically for the AI era, so your engineering team can focus on building user experiences instead of GIS pipelines. **See it live:** Explore our Neighborhood Intelligence Index on the interactive map at [map.ihuus.com](https://map.ihuus.com/) without writing a single line of code. *** ## Two Ways to Integrate Query our high-performance spatial index directly. Get credible, FHA-compliant, hyperlocal data in milliseconds: school ratings, noise levels, flood risk, and more. Plug Neighborhood Intelligence directly into AI agents via the Model Context Protocol. Structured for agentic reasoning, not hallucinations. Pre-built extensions for Claude Desktop and Gemini CLI available on [GitHub](https://github.com/ihuus/mcp). *** ## Intelligence Dimensions Every score is returned on a **0–255 scale** with a human-readable semantic description, ready for both programmatic use and LLM consumption. ### Schools & Ratings Search for K-12 schools and districts by geographic coordinates. Results include distance, level, ratings, and district metadata sourced from federal NCES datasets. Use the [Geocode endpoint](/api-reference/tools/geocode-a-single-address) to convert addresses to coordinates first. Find the closest schools to any lat/lon, with ratings, distance, and district info. Look up all overlapping school districts (Unified, Elementary, Secondary) at a location, including district-level ratings, rating summaries, and vintage year. All coordinate-based endpoints work seamlessly with AI agents. Our [Geocode tool](/api-reference/tools/geocode-a-single-address) lets LLMs convert addresses to coordinates automatically, so no extra integration work is needed. ### Vibe Captures the qualitative feel of a neighborhood: how private, walkable, visually appealing, dog-friendly, or urban/rural it is. Seclusion based on density, lot sizes, tree cover, and visibility. Sidewalks, intersection density, and proximity to amenities. Architectural character, landscaping, and streetscape quality. Parks, trails, off-leash areas, and pet-friendly businesses. Dense urban core to open countryside, classified from overhead imagery. Activity level and density of social destinations, from quiet enclaves to urban hotspots. ### Environment Quantifies the physical environment: acoustic comfort, air quality, and proximity to industrial or hazardous sites. Federal noise modelling for road, railroad, and aviation sources. AQI consistency derived from OpenAQ monitoring stations. EPA hazard data, Superfund sites, and industrial POI density. ### Demographics Population-level indicators derived from US Census Bureau data and voting records. Share of residents with health insurance coverage. Conservative-to-liberal spectrum from Census and voting data. Age distribution from young-adult-skewing to senior-skewing. ### Risk Natural hazard exposure derived from FEMA and CALFIRE authoritative datasets. Lower scores indicate higher risk. FEMA flood zone designations from coastal high-hazard to minimal risk. CALFIRE severity zones (California). Severe to no-risk classification. ### Tools Utility endpoints to support agentic workflows and data processing. Convert a free-text address into lat/lon coordinates. Built for single-shot agentic use. *** ## Why Build with iHuus? Skip the GIS pipeline. Structured, plug-and-play neighborhood data so you can focus on your product. Every response includes raw scores and human-readable descriptions, so your LLMs pass accurate context, not guesses. Pre-processed indices deliver actionable insights without crossing into protected demographic territory. *** ## Authentication All endpoints require a Bearer token issued on your [account dashboard](https://map.ihuus.com/account): | Method | Header | Description | | ---------------- | ------------------------------- | -------------------------------------------------------------------------------- | | **Bearer Token** | `Authorization: Bearer ` | Your API token issued on your [account dashboard](https://map.ihuus.com/account) | *** ## Quick Start Make your first API call in seconds. This example finds the closest schools to a location in San Jose, CA: ```bash theme={null} curl -G "https://api.ihuus.com/v1/schools/search/school-ratings" \ -H "Authorization: Bearer YOUR_API_TOKEN" \ -d lat=37.3382 \ -d lon=-121.8863 \ -d limit=3 ``` *** ## Get Started Connect iHuus to your AI agents via the Model Context Protocol. Explore all REST endpoints, parameters, and response schemas. *** ## Need Help? Questions about your API token, billing, or integration? Email us at **[support@ihuus.com](mailto:support@ihuus.com)** and we'll get back to you shortly.