# com.dropwatchhq/oracle

> MCP tools: collectible price-fairness, recall safety, drop tracking, card grading, settlements.

- name: com.dropwatchhq/oracle
- version: 1.0.0
- connection class: R0 (autonomous)
- trust: 76/100 flags: no-repository
- quality: 79/100 (good)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/com.dropwatchhq%2Foracle
- tools: https://api.protogrid.dev/v1/servers/com.dropwatchhq%2Foracle/tools

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

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "oracle": {
      "type": "http",
      "url": "https://oracle.dropwatchhq.com/mcp"
    }
  }
}
```


## Trust

- hygiene: 80
- liveness: 100
- freshness: 65
- provenance: 55
- drivers: +dns-namespace +website +reachable +uptime-100% ~updated-121d-ago -no-repository
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 79/100 (good)

### protocol: 75 (weight 25)

- warn `protocol.modern`: newest supported version is 2024-11-05; 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: 71 (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
- fail `tools.annotations`: no tool declares readOnlyHint or destructiveHint, so clients cannot tell safe calls from risky ones
- fail `tools.directory_hints`: no tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: check_scalper_price (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); check_in_stock (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); grade_card_centering (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); …
- pass `tools.token_cost`: about 744 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: 5, about 744 tokens to load them all
- tool set hash: 76f6228faba71ff88c89f32038b04303
- badge: [![protogrid quality](https://protogrid.dev/badge/com.dropwatchhq/oracle.svg)](https://protogrid.dev/servers/com.dropwatchhq/oracle)
- 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://oracle.dropwatchhq.com/mcp (streamable-http, auth none, reachable true, uptime30d 1)

## Packages

_none_

## Tools (5)

- `check_in_stock`: Check whether a hobby item has recently dropped or restocked across the specialty shops we monitor for a niche. Returns recent in-stock matches (new + restock) with direct buy links. Use when an agent wants to find where a sold-out collectible is currently available.
- `check_recall`: Search active consumer product recalls (CPSC, FDA, NHTSA and more) by keyword. Returns matching recalls with agency, hazard, affected products, and remedy. Use when an agent needs to know if a product, brand, baby/food/vehicle item has been recalled before recommending or buying it.
- `check_scalper_price`: Check whether a hobby item's asking price is fair or scalped. Compares a price you're seeing against current retail across tracked specialty shops for the niche. Returns a verdict (fair/high/scalped), the retail price band, and where to buy at retail. Use when an agent or user wants to know if a Pokémon box, LEGO set, Funko, keyboard, vinyl, or aquarium item is overpriced.
- `find_settlements`: Find open class-action settlements you may be eligible to claim (often no proof of purchase required). Returns settlements with payout, claim deadline, proof requirements, and the official claim URL. Use when an agent wants to surface free-money / consumer-rights opportunities for a user.
- `grade_card_centering`: Estimate a trading card's centering and rough PSA-style grade from a photo. NOTE: the centering measurement runs client-side in the browser (computer vision on the uploaded image) and is not server-callable here. This tool returns guidance plus a link to the live CardGrade tool where the agent or user can run the analysis.