# IDPhoto.ai Passport & Visa Photos

> Turn a portrait into a compliant passport, visa or ID photo. 300+ official specs, 3 free a day.

- name: ai.idphoto/mcp
- version: 0.1.0
- connection class: R0 (autonomous)
- trust: 83/100 flags: no-repository
- quality: 85/100 (new)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/ai.idphoto%2Fmcp
- tools: https://api.protogrid.dev/v1/servers/ai.idphoto%2Fmcp/tools

**An agent can connect right now, no human step.** Remote endpoint, no authentication, reachable on the last probe.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "idphoto": {
      "type": "http",
      "url": "https://mcp.idphoto.ai/mcp",
      "headers": {
        "X-IDP-API-Key": "${X_IDP_API_KEY}",
        "X-IDP-API-Secret": "${X_IDP_API_SECRET}"
      }
    }
  }
}
```

Placeholders to fill: `${X_IDP_API_KEY}`, `${X_IDP_API_SECRET}`.

## Trust

- hygiene: 80
- liveness: 100
- freshness: 100
- provenance: 55
- drivers: +dns-namespace +website +reachable +uptime-100% +updated-1d-ago -no-repository
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 85/100 (new)

### protocol: 75 (weight 25)

- warn `protocol.modern`: newest supported version is 2025-11-25; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
- n/a `protocol.stateless`: only applies to 2026-07-28 servers
- pass `protocol.transport`: streamable HTTP
- n/a `protocol.list_ttl`: only applies to 2026-07-28 servers

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 93 (weight 30)

- pass `tools.descriptions`: every tool has a description
- pass `tools.description_length`: descriptions are concise
- pass `tools.schemas`: every tool has an object input schema
- pass `tools.annotations`: 4 of 4 tools declare readOnlyHint or destructiveHint
- warn `tools.directory_hints`: 1 of 4 tools declare all four hints; missing: get_photo_spec (destructiveHint, idempotentHint); get_usage (destructiveHint, idempotentHint); list_photo_specs (destructiveHint, idempotentHint)
- pass `tools.token_cost`: about 540 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: n/a (weight 15)

- n/a `stability.changes`, `stability.rug_pull`: tool history recorded for 1 of the 7 days needed

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package

- tools: 4, about 540 tokens to load them all
- tool set hash: 97d26ddc75a13417e374264a45c3f901
- tools last changed: 2026-10-20T03:44:55.711Z
- badge: [![protogrid quality](https://protogrid.dev/badge/ai.idphoto/mcp.svg)](https://protogrid.dev/servers/ai.idphoto/mcp)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

- 2026-10-20 `make_id_photo` changed (inputSchema)

Full history: https://api.protogrid.dev/v1/servers/ai.idphoto%2Fmcp/changes

## Remotes

- https://mcp.idphoto.ai/mcp (streamable-http, auth none, reachable true, uptime30d 1)

## Packages

_none_

## Tools (4)

- `get_photo_spec`: Get the detailed requirements of one photo spec: physical size, pixel size, DPI, background color, head height / eye position guidance, glasses and expression rules.
- `get_usage`: Show remaining quota. With API credentials: the idphoto.ai account status and remaining make-photo quota. Without credentials: how many free make_id_photo calls are left today.
- `list_photo_specs`: List all supported passport / visa / ID photo specifications as specCode + human-readable name (e.g. 'us-passport' = 'US Passport'). Use this to find the specCode for make_id_photo.
- `make_id_photo`: Turn a portrait photo into a compliant passport / visa / ID photo for a given document spec (cropping, resizing, background replacement, quality checks). Returns a temporary download URL for the finished JPEG, its pixel/physical size, and any detected quality issues (e.g. ISSUE_EYEGLASSES_NOT_ALLOWED) that may require a retake. Use list_photo_specs or get_photo_spec first if you are unsure of the specCode. The input image must be base64 (data URI prefix allowed), at most ~4 MB decoded, showing one person facing the camera. Without API credentials this is limited to 3 photos per day.