# Atly

> Find places by what you want (work friendly, gluten free, great coffee), scored from real reviews.

- name: com.atly/places
- version: 1.0.1
- connection class: R0 (autonomous)
- trust: 96/100
- quality: 85/100 (good)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/com.atly%2Fplaces
- tools: https://api.protogrid.dev/v1/servers/com.atly%2Fplaces/tools

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

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "places": {
      "type": "http",
      "url": "https://agentic-api.atly.com/mcp",
      "headers": {
        "X-API-Key": "${X_API_KEY}"
      }
    }
  }
}
```

Placeholders to fill: `${X_API_KEY}`.

## Trust

- hygiene: 100
- liveness: 100
- freshness: 100
- provenance: 85
- drivers: +repository +dns-namespace +website +reachable +uptime-100% +updated-15d-ago
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 85/100 (good)

### 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: 86 (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`: 7 of 7 tools declare readOnlyHint or destructiveHint
- fail `tools.directory_hints`: no tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: get_api_key (idempotentHint); list_categories (idempotentHint); list_areas (idempotentHint); …
- pass `tools.token_cost`: about 1,371 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: 100 (weight 15)

- pass `stability.changes`: no tool changes in 30 days
- pass `stability.rug_pull`: no tool changed its meaning under the same name

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

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

- tools: 7, about 1,371 tokens to load them all
- tool set hash: 6057d1d3f22cf2853bade5fa98b81a08
- badge: [![protogrid quality](https://protogrid.dev/badge/com.atly/places.svg)](https://protogrid.dev/servers/com.atly/places)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

_No tool definition changes recorded._

## Remotes

- https://agentic-api.atly.com/mcp (streamable-http, auth none, reachable true, uptime30d 1)

## Packages

_none_

## Tools (7)

- `get_api_key`: Show my key, tier and remaining quota

Who am I and how much quota is left. Works without a key too (then it describes the anonymous allowance for your IP).
- `get_docs`: Read the documentation

Returns the API guide as Markdown: what each operation is for, how to turn a user's request into
category ids and a location, request and response shapes, how to read scores. Call this once per session.
- `get_place`: Everything about one place

Full detail for a place id from `search_places`: profile, hours, all category scores, up to eight quotable
statements, good-to-know facts, gluten-free identity when known, and the canonical Atly URL to cite.
- `list_areas`: List supported areas

Cities, neighborhoods and states Atly covers — densest in the United States, with pockets in Mexico, Israel and Thailand — each with an `id` you can pass to
search, a center, a bounding box when known, and how many places it holds. Filter with `q` (substring of
the name) and `level` (city, neighborhood, state). Results are ordered by place count.
- `list_categories`: List intent categories

The intent taxonomy: cuisines, dishes, features ("Wifi", "Outdoor Seating"), vibes ("Cozy", "Lively"),
occasions ("First Date", "Group Dinner"), diets ("Gluten Free", "Keto") and more. Map the user's words to
category ids before searching. Filter with `q`, one concept per call — exact and prefix matches rank first, then substrings and keywords;
plurals, hyphens and small typos are tolerated — or fetch once without `q` and cache the full list.
- `search_places`: Find places for an intent near a location

The core call. Give one or more category ids (from `list_categories`; all must match) and a location — either
an `area_id` from `list_areas` or coordinates with a radius — and get places ranked by Atly's score for those
categories, each with quotable reasons from real reviews, a link to cite, and freshness. Scores are 0–10 and
relative to the area; a place with no score is unmeasured, not bad. If no place matches every category, trailing
categories are dropped until something does (the first is never dropped), and `dropped_categories` says which.
Ranking considers the strongest 100 candidates by Atly's base score. Scores are relative to other places in the same country.
- `submit_feedback`: Tell us how a call went

Reference the `call_id` of any earlier response and say whether it helped, and optionally why, in a sentence
about the result — what was right, missing or wrong. Do not include the user's words, the conversation, or
anything about the person. One row per caller per call; lightly rate-limited.