# modelright

> Live registry of AI model specs, context windows, and per-token pricing.

- name: dev.modelright/modelright
- version: 0.1.0
- connection class: R0 (autonomous)
- trust: 95/100
- quality: 83/100 (good)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/dev.modelright%2Fmodelright
- tools: https://api.protogrid.dev/v1/servers/dev.modelright%2Fmodelright/tools

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

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "modelright": {
      "type": "http",
      "url": "https://modelright.dev/api/mcp"
    }
  }
}
```


## Trust

- hygiene: 100
- liveness: 99
- freshness: 100
- provenance: 85
- drivers: +repository +dns-namespace +website +reachable +uptime-98% +updated-12d-ago
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 83/100 (good)

### protocol: 88 (weight 25)

- pass `protocol.modern`: supports 2026-07-28 (server/discover)
- pass `protocol.stateless`: answers without a session
- pass `protocol.transport`: streamable HTTP
- warn `protocol.list_ttl`: tools/list declares ttlMs 0, so clients re-fetch it on every use

### 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: get_ingest_status (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); list_models (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); get_model (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); …
- pass `tools.token_cost`: about 758 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: 6, about 758 tokens to load them all
- tool set hash: d58c62ba1608033cc2c862e24cc8f246
- badge: [![protogrid quality](https://protogrid.dev/badge/dev.modelright/modelright.svg)](https://protogrid.dev/servers/dev.modelright/modelright)
- 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://modelright.dev/api/mcp (streamable-http, auth none, reachable true, uptime30d 0.98)

## Packages

_none_

## Tools (6)

- `compare_models`: Side-by-side comparison of 2-10 models by provider/slug: context window, input/output price per 1M tokens, modalities, status.
- `get_ingest_status`: Data-freshness check: registry totals and the most recent ingest runs (source, model count, status, time).
- `get_model`: Full detail for one model (provider+slug from search_models): specs, current price, status, and recent price/availability snapshots.
- `list_models`: List tracked models with pricing and context windows. Filter by provider, modality tag, status, or price/context bounds.
- `list_providers`: List providers tracked by the registry with their model counts. Use provider slugs in list_models / get_model / compare_models.
- `search_models`: Substring search across model name, slug, and provider — the fast path to a model's provider/slug pair for the detail tools.