modelright
Measured conclusion: Alive, not deep-tested. L2 outcome: not_attempted.
Live registry of AI model specs, context windows, and per-token pricing.
| Author | dev.modelright |
|---|---|
| Access | remote |
| Publisher key required | No |
| Measured state | Alive, not deep-tested |
| L1 liveness | alive |
| L1 latency | 2685 ms |
| Last measured | 2026-10-26 |
Add to your agent
Copy this into your MCP client config:
{
"mcpServers": {
"modelright": {
"url": "https://modelright.dev/api/mcp",
"transport": "streamable-http"
}
}
}
Measured tools (6)
list_providersList providers tracked by the registry with their model counts. Use provider slugs in list_models / get_model / compare_models.
Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared
search_modelsSubstring search across model name, slug, and provider — the fast path to a model's provider/slug pair for the detail tools.
Parameters:
q(required) — string — Search text, e.g. 'sonnet'limit— integer — Max results (default 20)
Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared
list_modelsList tracked models with pricing and context windows. Filter by provider, modality tag, status, or price/context bounds.
Parameters:
sort— string — Sort order (default name)limit— integer — Max results (default 100)status— string — Status filter, e.g. 'available', 'deprecated'modality— string — Modality tag filter, e.g. 'text', 'image', 'audio'provider— string — Provider slug filter, e.g. 'anthropic'minContextWindow— integer — Minimum context windowmaxInputPricePerM— number — Max input price per 1M tokens (USD)
Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared
get_modelFull detail for one model (provider+slug from search_models): specs, current price, status, and recent price/availability snapshots.
Parameters:
provider(required) — string — Provider slug, e.g. 'openai'slug(required) — string — Model slug, e.g. 'gpt-4o'snapshots— integer — Recent snapshots to include (default 10, 0 to skip)
Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared
compare_modelsSide-by-side comparison of 2-10 models by provider/slug: context window, input/output price per 1M tokens, modalities, status.
Parameters:
models(required) — array — Models to compare
Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared
get_ingest_statusData-freshness check: registry totals and the most recent ingest runs (source, model count, status, time).
Parameters:
limit— integer — Recent ingest runs to return (default 10)
Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared
Measured by MCPYP probing. Untested fields are omitted, never estimated. Listing is always free; MCPYP never proxies calls or stores user tokens.