modelright

Official6 tools

by homezloco · TypeScript

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

Model Context Protocol (MCP) Server: dev.modelright/modelright

This MCP server provides a live registry of AI model specifications, including context windows and per-token pricing. Its catalog-style content supports discovery of model details and cost information, based on the model specs it exposes.

🛠️ Key Features

Live registry of AI model specs
Includes context windows
Includes per-token pricing

🚀 Use Cases

Locate AI model context window sizes for planning
Compare per-token pricing for budgeting

⚡ Developer Benefits

Centralized access to model specifications, context windows, and pricing

⚠️ Limitations

Description only specifies registry coverage (specs, context windows, per-token pricing); no other capabilities are indicated.

Topics

ai-modelsdrizzle-ormllmmcp-servermodel-registrynextjs

Captured live from the server via tools/list.

list_providers

List providers tracked by the registry with their model counts. Use provider slugs in list_models / get_model / compare_models.

Parameters

No parameters.

Raw schema

{
  "type": "object",
  "properties": {}
}

search_models

Substring search across model name, slug, and provider — the fast path to a model's provider/slug pair for the detail tools.

Parameters2

q	string	required	Search text, e.g. 'sonnet'
limit	integer	optional	Max results (default 20)

Raw schema

{
  "type": "object",
  "properties": {
    "q": {
      "type": "string",
      "minLength": 1,
      "maxLength": 100,
      "description": "Search text, e.g. 'sonnet'"
    },
    "limit": {
      "description": "Max results (default 20)",
      "type": "integer",
      "minimum": 1,
      "maximum": 100
    }
  },
  "required": [
    "q"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema"
}

list_models

List tracked models with pricing and context windows. Filter by provider, modality tag, status, or price/context bounds.

Parameters7

provider	string	optional	Provider slug filter, e.g. 'anthropic'
modality	string	optional	Modality tag filter, e.g. 'text', 'image', 'audio'
status	string	optional	Status filter, e.g. 'available', 'deprecated'
minContextWindow	integer	optional	Minimum context window
maxInputPricePerM	number	optional	Max input price per 1M tokens (USD)
sort	string	optional	Sort order (default name)
limit	integer	optional	Max results (default 100)

Raw schema

{
  "type": "object",
  "properties": {
    "provider": {
      "description": "Provider slug filter, e.g. 'anthropic'",
      "type": "string"
    },
    "modality": {
      "description": "Modality tag filter, e.g. 'text', 'image', 'audio'",
      "type": "string"
    },
    "status": {
      "description": "Status filter, e.g. 'available', 'deprecated'",
      "type": "string"
    },
    "minContextWindow": {
      "description": "Minimum context window",
      "type": "integer",
      "exclusiveMinimum": 0,
      "maximum": 9007199254740991
    },
    "maxInputPricePerM": {
      "description": "Max input price per 1M tokens (USD)",
      "type": "number",
      "minimum": 0
    },
    "sort": {
      "description": "Sort order (default name)",
      "type": "string",
      "enum": [
        "name",
        "input_price_asc",
        "input_price_desc",
        "context_desc"
      ]
    },
    "limit": {
      "description": "Max results (default 100)",
      "type": "integer",
      "minimum": 1,
      "maximum": 500
    }
  },
  "$schema": "https://json-schema.org/draft/2020-12/schema"
}

get_model

Full detail for one model (provider+slug from search_models): specs, current price, status, and recent price/availability snapshots.

Parameters3

provider	string	required	Provider slug, e.g. 'openai'
slug	string	required	Model slug, e.g. 'gpt-4o'
snapshots	integer	optional	Recent snapshots to include (default 10, 0 to skip)

Raw schema

{
  "type": "object",
  "properties": {
    "provider": {
      "type": "string",
      "minLength": 1,
      "description": "Provider slug, e.g. 'openai'"
    },
    "slug": {
      "type": "string",
      "minLength": 1,
      "description": "Model slug, e.g. 'gpt-4o'"
    },
    "snapshots": {
      "description": "Recent snapshots to include (default 10, 0 to skip)",
      "type": "integer",
      "minimum": 0,
      "maximum": 50
    }
  },
  "required": [
    "provider",
    "slug"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema"
}

compare_models

Side-by-side comparison of 2-10 models by provider/slug: context window, input/output price per 1M tokens, modalities, status.

Parameters1

models

array

required

Models to compare

Raw schema

{
  "type": "object",
  "properties": {
    "models": {
      "minItems": 2,
      "maxItems": 10,
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "provider": {
            "type": "string",
            "minLength": 1,
            "description": "Provider slug, e.g. 'openai'"
          },
          "slug": {
            "type": "string",
            "minLength": 1,
            "description": "Model slug, e.g. 'gpt-4o'"
          }
        },
        "required": [
          "provider",
          "slug"
        ]
      },
      "description": "Models to compare"
    }
  },
  "required": [
    "models"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema"
}

get_ingest_status

Data-freshness check: registry totals and the most recent ingest runs (source, model count, status, time).

Parameters1

limit

integer

optional

Recent ingest runs to return (default 10)

Raw schema

{
  "type": "object",
  "properties": {
    "limit": {
      "description": "Recent ingest runs to return (default 10)",
      "type": "integer",
      "minimum": 1,
      "maximum": 50
    }
  },
  "$schema": "https://json-schema.org/draft/2020-12/schema"
}

README.md4 KBView on GitHub

modelright

Live registry of AI model specs, context windows, and per-1M-token pricing — running at modelright.dev.

A Next.js + Postgres app that keeps a real, current catalog of LLMs: the OpenRouter catalog is synced hourly, Artificial Analysis enriches models with benchmark and speed data, and every price change lands in an append-only snapshot log that powers the changes feed and price-history charts.

modelright models index

What's in it

Catalog — /models searchable/filterable by provider, status, price ceiling, context floor, modality, and free-tier; /providers directory
Model detail — specs, pricing, price-history chart, cost calculator, Artificial Analysis benchmark card (/models/[provider]/[slug])
Compare — up to 4 models side-by-side with an interactive picker and cheapest-highlighting (/compare); SEO-friendly pair pages at /compare/a-vs-b
Task picks — /pick and /pick/{chat,coding,long-context,vision,cheap-bulk} rank models by an explicit rule written on the page
Changes feed — /changes lists recent price/status changes and model additions/removals, with an RSS feed
Public API — GET /api/v1/models (same filters as the UI), /api/v1/models/{provider}/{slug}, /api/v1/providers, /api/v1/changes; OpenAPI at /openapi.json
MCP server — Streamable-HTTP endpoint at /api/mcp (also /.well-known/mcp) with six read tools (search_models, get_model, list_providers, compare_models, get_changes, get_ingest_status)
Agent surfaces — /llms.txt, /agents.txt, A2A agent card (/.well-known/agent-card.json), Smithery server card (/.well-known/mcp/server-card.json), server.json MCP-registry listing
Analytics — cookieless page-view beacon (daily-rotating salted visitor hash, no raw IPs), edge-middleware AI-crawler tracking (/api/bot-hit), and MCP call logging, all rendered on a token-gated /admin + /admin/analytics
Ingest pipeline — POST /api/ingest (Bearer token, zod-validated, idempotent upsert) and POST /api/cron/sync (hourly OpenRouter + AA sync, marks removed models rather than deleting)

Stack

Next.js 14 (App Router, edge middleware) + React 18 + TypeScript
Drizzle ORM over PostgreSQL (postgres driver) — migrations in drizzle/
mcp-handler for the MCP Streamable-HTTP transport
Vitest + happy-dom — 200+ tests, ~90% line coverage on src/lib + src/app/api

Setup

bash

npm install
cp .env.example .env   # set DATABASE_URL
npm run db:migrate
npm run db:seed        # optional fixture data so pages render pre-ingest
npm run dev            # http://localhost:3000

Scripts

Script	Purpose
`npm run dev` / `build` / `start`	Next.js lifecycle
`npm run typecheck`	`tsc --noEmit`
`npm run test`	Vitest with coverage
`npm run db:generate` / `db:migrate` / `db:seed`	Drizzle schema lifecycle + fixtures

Environment

See .env.example. Highlights: DATABASE_URL (required), INGEST_TOKEN + CRON_SECRET (write-path auth), AA_API_KEY (Artificial Analysis enrichment), ADMIN_TOKEN (gates /admin), ANALYTICS_SALT (daily visitor-hash salt — rotate to reset identities).

Built autonomously

This repo is maintained by a LiveGraph improvement loop: queued items in QUEUE.md are picked up, implemented, tested, and merged by agents. PLAN.md holds the product roadmap, docs/loop-reports/ is the per-item delivery log, and GROWTH.md/growth/assets/ hold the distribution plan and media kit (including a walkthrough video). If you're evaluating agent-driven development, the queue history and loop reports are the interesting part.

License

MIT — see LICENSE.

Install

Tools (6)

list_providerssearch_modelslist_modelsget_modelcompare_modelsget_ingest_status

Remote endpoint

Streamable HTTP

Hosted server - connect over the network, no local install.

url

https://modelright.dev/api/mcp

Add to VS Code Add to Cursor

claude_desktop_config.json

json

{
  "mcpServers": {
    "modelright": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://modelright.dev/api/mcp"
      ]
    }
  }
}

Desktop config is stdio-only; this bridges via mcp-remote. Native remote: Settings > Connectors.

Model Context Protocol (MCP) Server: dev.modelright/modelright

🛠️ Key Features

🚀 Use Cases

⚡ Developer Benefits

⚠️ Limitations

Topics

list_providers

search_models

list_models

get_model

compare_models

get_ingest_status

modelright

What's in it

Stack

Setup

Scripts

Environment

Built autonomously

License

Install

Remote endpoint

Related servers