What is Mireye
Mireye is infrastructure for physical-world AI agents, providing one API and MCP to connect agents to the physical world with accurate data enrichment, signals, and tools. It serves as the physical-world layer for AI agents, offering sourced data, enrichment, and tools on top of them. The platform enables users to ask questions in natural language, resolve addresses to canonical parcels, or fetch cited fields at any US coordinate, with a citation attached to every field.
How to use Mireye
Mireye can be used through its API endpoints or MCP server. The main endpoints include:
- /v1/ask: Ask anything about a place
- /v1/geocode: Turn anything into a place
- /v1/lookup: One string, the whole stack
- /v1/fetch: Cited facts at any location
- /v1/proximity: Measure what the data can't say
- /v1/field-requests: Request a field that doesn't exist
To get started, sign up for an account, obtain API credentials, and integrate the endpoints into your AI agent or application. Detailed documentation is available.
Features of Mireye
- One API and MCP server for physical-world data
- Natural language querying of places
- Address resolution to canonical parcels
- Fetching cited fields at any US coordinate
- Citation attached to every field (source name, source URL, fetched_at timestamp, confidence level)
- 85 authoritative sources, primarily federal datasets (USGS, FEMA, NOAA, USDA, BLM, EPA, EIA, etc.)
- Coverage: United States for data catalog; drive-time analysis (/v1/proximity) covers US and Canada
- Field requests: order a field that doesn't exist, and it will be researched, built, and validated
- Credit-based pricing with free tier
Use Cases of Mireye
- AI agents making decisions based on physical-world data
- Enriching applications with geospatial context
- Resolving addresses to canonical parcels
- Fetching cited facts at any location
- Measuring proximity and drive-time analysis
- Requesting custom fields for specific needs
Pricing
Mireye uses credit-based pricing. The free tier includes 5,000 credits per month with no credit card required. Paid plans start at $19 per month. No plan bills past its allowance; usage stops rather than incurring overages. Credits are the unit across all endpoints, and the credit price per call type is published on the pricing page.
FAQ
What does Mireye actually do? Mireye is the physical-world layer for AI agents: sourced data, enrichment, and the tools on top of them. Ask a question in natural language, resolve an address to its canonical parcel, or fetch cited fields at any US coordinate — one API and one MCP server, with a citation attached to every field.
What does it cost? Credit-based pricing. The free tier is 5,000 credits a month with no card; paid plans start at $19/mo, and no plan bills past its allowance — usage stops rather than running up an overage. Credits are the unit across all endpoints, and the credit price per call type is published on the pricing page.
What region does Mireye cover? United States for the data catalog, with one exception: drive-time analysis (/v1/proximity) covers the US and Canada. Most of the catalog is US federal (USGS, FEMA, NOAA, USDA, BLM, EPA, EIA and more), with a few open and licensed additions such as Overture and Sentinel-2. Every value carries its own source, so you can always see which one you are relying on.
Where does the data come from? 85 authoritative sources, federal datasets primarily, plus county records and open datasets. Every field in every response returns a source name, a source URL, a fetched_at timestamp, and a confidence level so the agent can pass provenance straight through to the end user or auditor.
How fresh is the data? It varies by layer. Elevation (USGS 3DEP) is effectively static. FEMA flood maps refresh on FEMA's cadence. USDA cropland updates yearly. Every response includes the fetched_at timestamp so the agent always knows what it is looking at.
What if the field I need doesn't exist? Order it. Every plan includes field requests — file one and we research, build and validate the field, then notify you when it goes live: permanently, for every future caller. Requests are matched against the catalog first, and honestly rejected when they can't be built.
