# Mireye

- [Introduction](https://docs.mireye.ai/introduction.md): Infrastructure for physical-world AI agents. One API for data, enrichment, tools, and signals — every value cited.
- [Quickstart](https://docs.mireye.ai/quickstart.md): Five minutes from zero to a cited answer about any US location — curl, jq, and a token.
- [Authentication](https://docs.mireye.ai/authentication.md): Bearer tokens for /v1/ask, /v1/fetch, and the hosted MCP endpoint.
- [Pricing and credits](https://docs.mireye.ai/pricing.md): What each call costs in credits, what each plan includes, and how to price a job before you run it.
- [POST /v1/ask](https://docs.mireye.ai/api-reference/ask.md): Natural-language Q&A over US coordinates with per-citation provenance.
- [POST /v1/ask/stream](https://docs.mireye.ai/api-reference/ask-stream.md): The streaming variant of /v1/ask — first tokens in about five seconds instead of waiting for the whole answer.
- [POST /v1/fetch](https://docs.mireye.ai/api-reference/fetch.md): Deterministic per-field data fetch with full provenance.
- [POST /v1/fetch/batch](https://docs.mireye.ai/api-reference/fetch-batch.md): The same field fetch for up to 25 locations in one request.
- [POST /v1/fetch/quote](https://docs.mireye.ai/api-reference/fetch-quote.md): What a fetch would cost, and whether your allowance covers it — before you run it.
- [POST /v1/runs](https://docs.mireye.ai/api-reference/runs.md): Submit a job, get a run_id immediately, poll or stream its progress.
- [GET /v1/runs/{run_id}/events](https://docs.mireye.ai/api-reference/run-events.md): Watch a batch run's progress as Server-Sent Events instead of polling.
- [GET /v1/runs/{run_id}/artifacts/{fmt}](https://docs.mireye.ai/api-reference/run-artifacts.md): Download a finished run as CSV or GeoJSON — rendered on read, no export step.
- [POST /v1/sites](https://docs.mireye.ai/api-reference/sites.md): Register an area of interest once, screen it once, then ask it questions cheaply for as long as it exists.
- [POST /v1/ask-site](https://docs.mireye.ai/api-reference/ask-site.md): Ask a registered polygon a question — one model call over a dossier that was screened once.
- [POST /v1/geocode](https://docs.mireye.ai/api-reference/geocode.md): Resolve a US street address to a coordinate, with the quality of that coordinate.
- [POST /v1/lookup](https://docs.mireye.ai/api-reference/lookup.md): Resolve an address, coordinate, or APN to canonical join keys: a coordinate, resolved address, and — when it's safe to — a parcel.
- [POST /v1/proximity](https://docs.mireye.ai/api-reference/proximity.md): Drive-time distance, nearest-candidate, proximity screening, and labor-shed compute across multiple US + Canada coordinates.
- [GET /v1/meta/fields](https://docs.mireye.ai/api-reference/meta-fields.md): Self-discovery: field + preset catalog with ETag-based caching.
- [Field catalog](https://docs.mireye.ai/api-reference/field-catalog.md): Full reference of every field exposed by /v1/fetch and /v1/ask.
- [POST /v1/field-requests](https://docs.mireye.ai/api-reference/field-requests.md): Request a field: ask for any US-location data point in plain language. If the catalog already answers it you get the value now, with a citation; if not, we build it and notify you.
- [GET /v1/field-requests/{request_id}](https://docs.mireye.ai/api-reference/field-requests-status.md): Poll a field request: status, queue position, the promised ETA, and — once the field is live — the resume call that answers your original ask.
- [Errors](https://docs.mireye.ai/api-reference/errors.md): Structured error codes returned by /v1/* endpoints.
- [Install](https://docs.mireye.ai/mcp/installation.md): Wire Mireye into Claude Desktop, Claude Code, Cursor, or a custom MCP agent.
- [MCP tools, resources, and prompts](https://docs.mireye.ai/mcp/tools.md): Mireye's MCP surface: seven tools, catalog resources, and workflow prompts.
- [Troubleshooting](https://docs.mireye.ai/mcp/troubleshooting.md): Common failures wiring up the MCP server, and how to fix them.

## OpenAPI Specs

- [openapi](https://api.mireye.com/v1/openapi.json)