# Mireye

**Canonical:** https://apis.io/providers/mireye/  
**Website:** https://docs.mireye.ai  
**APIs profiled:** 17

Mireye is infrastructure for physical-world AI agents, turning any US latitude and longitude into sourced, structured geospatial ground truth. Its Mireye Earth API exposes two HTTP endpoints — POST /v1/fetch for deterministic per-field values and POST /v1/ask for natural-language, citation-backed Q&A — plus GET /v1/meta/fields for a self-describing catalog of 175+ fields across seven layers (terrain, land cover, built environment, utilities and energy, climate and resource, hazards, and parcels and boundaries) and 14 preset bundles. Every value carries provenance: the source identifier, upstream URL, dataset vintage, timestamp, and a confidence rating, sourced from federal agencies (USGS, NOAA, USDA, USFS, FEMA, EPA, EIA, NREL, US Census) and open and commercial datasets (Sentinel-2, Overture Maps, Regrid). Mireye also runs a hosted OAuth 2.1 MCP server (com.mireye/earth) and a local stdio adapter so agents in Claude, Cursor, and custom loops can query the earth as easily as the web. Founded 2026 by Ansh Chokshi and Shashwat Kapoor; Y Combinator S26.

## Kin Score — 47.4 / 100 (developing)

Scored 2026-08-20 under rubric 0.12.0. Trend: flat (+1.1 from 46.3).

| Facet | Score |
|---|---|
| Discoverability | 92.6 |
| Contract Quality | 40.5 |
| Governance | 16.7 |
| Contract Governance | 16.7 |
| Operational Transparency | 2.6 |
| Developer Ergonomics | 71.4 |
| Commercial Clarity | 34.2 |
| Access Clarity | 34.2 |

Regulatory layer — **Insurance**: 57.6 (matched via tags).

## Agent readiness — 47.4 (agent-ready)

| Dimension | Value |
|---|---|
| Spec Presence | yes |
| Agentic Access | derived |
| Reversibility Documented | no |
| MCP Server | verified |
| Auth Clarity | yes |
| Idempotency | no |
| Error Semantics | verified |
| OpenAPI Examples | no |
| Rate Limit Signal | no |
| Event Surface Described | no |
| Agent Skills | yes |
| Well Known Catalog | no |
| Consent Identity | no |
| Agent Card | no |
| Dry Run Mode | no |

## Access

Self-serve signup — onboarding: self-serve, pricing: unknown, trial: no (confidence: medium).

## APIs (17)

- **Mireye Ask API** — The Ask API from Mireye — 2 operation(s) for ask.
- **Mireye Ask Site API** — The Ask Site API from Mireye — 1 operation(s) for ask site.
- **Mireye Auth API** — The Auth API from Mireye — 1 operation(s) for auth.
- **Mireye Authorize API** — The Authorize API from Mireye — 1 operation(s) for authorize.
- **Mireye Feature Requests API** — The Feature Requests API from Mireye — 1 operation(s) for feature requests.
- **Mireye Fetch API** — The Fetch API from Mireye — 1 operation(s) for fetch.
- **Mireye Healthz API** — The Healthz API from Mireye — 1 operation(s) for healthz.
- **Mireye Mcp API** — The Mcp API from Mireye — 3 operation(s) for mcp.
- **Mireye Meta API** — The Meta API from Mireye — 1 operation(s) for meta.
- **Mireye Oauth API** — The Oauth API from Mireye — 4 operation(s) for oauth.
- **Mireye Readyz API** — The Readyz API from Mireye — 1 operation(s) for readyz.
- **Mireye Register API** — The Register API from Mireye — 1 operation(s) for register.
- **Mireye Revoke API** — The Revoke API from Mireye — 1 operation(s) for revoke.
- **Mireye Sites API** — The Sites API from Mireye — 2 operation(s) for sites.
- **Mireye Token API** — The Token API from Mireye — 1 operation(s) for token.
- **Mireye Users API** — The Users API from Mireye — 5 operation(s) for users.
- **Mireye .well Known API** — The .well Known API from Mireye — 1 operation(s) for .well known.

## MCP servers (1)

- **Mireye MCP Server**

## Agentic access (1)

- **Mireye Agentic Access** — 30 operations · 22 acting · 3 human-in-the-loop

## Security (2)

- **Mireye Authentication** — http/oauth2 · 3 schemes
- **Mireye Domain Security** — TLSv1.3 · HSTS · DMARC

## Tags

Company, Geospatial, Geographic Information System, Location, AI Agents, MCP, Government Data, Risk, Insurance, Data

---

Profiled by [API Evangelist](https://apievangelist.com) and published on [APIs.io](https://apis.io/providers/mireye/). Scores are computed from the provider's own public artifacts under a published rubric.