{
  "markdown": "# frontdesk-data\n\n<!--\nabstract: Independent, sourced product and software data — 4,764 products across 359 hardware categories and 267 software categories. Every figure is traced to its source URL and access date; unknown values are null, never a guess. Queryable live over MCP. CC-BY-4.0. Version 2026-06-12.\nlicense: CC-BY-4.0\nhomepage: https://frontdeskreview.com/data\n-->\n\nIndependent, sourced data on what things cost and how they actually perform.\n**4,764 products** across **359 hardware categories**, plus software pricing across\n**267 categories** — every figure traced to its source (the vendor's own page URL and the date\nwe captured it). Quote-only tiers and unknown specs are recorded as null rather than guessed.\nNothing is invented.\n\n**Current version:** 2026-06-12.\n\n## Query it live from an AI assistant (MCP)\n\nThis dataset is served by a live **Model Context Protocol** server. No API key, no account,\nread-only. Every record an assistant receives carries its source URL and capture date, so any\nfigure it repeats can be cited.\n\n**Endpoint:** `https://mcp.frontdeskreview.com/mcp` (Streamable HTTP)\n\nClaude Code:\n\n```bash\nclaude mcp add --transport http front-desk-review https://mcp.frontdeskreview.com/mcp\n```\n\nClaude Desktop, Cursor, Cline, Windsurf — add to the client's MCP config:\n\n```json\n{\n  \"mcpServers\": {\n    \"front-desk-review\": {\n      \"type\": \"streamable-http\",\n      \"url\": \"https://mcp.frontdeskreview.com/mcp\"\n    }\n  }\n}\n```\n\nVS Code (Copilot agent) — `.vscode/mcp.json` uses a top-level `servers` key:\n\n```json\n{\n  \"servers\": {\n    \"front-desk-review\": {\n      \"type\": \"http\",\n      \"url\": \"https://mcp.frontdeskreview.com/mcp\"\n    }\n  }\n}\n```\n\nChatGPT, Claude and Perplexity can add it from their own connector settings — paste the endpoint\nand leave authentication set to **None**. Setup for every client:\nhttps://frontdeskreview.com/connect/\n\nRegistry entry: `com.frontdeskreview/front-desk-review-data` · server card: https://mcp.frontdeskreview.com/mcp/server-card\n\n## Tools\n\nAll 19 are read-only and annotated as such, so a client can call them without prompting\non every request.\n\n| Tool | What it answers |\n| --- | --- |\n| `list_sections` | Every software/SaaS pricing theme covered, with slug, label and vendor count. |\n| `search_vendors` | Free-text search across a theme's vendors — names, domains, integrations, plan notes, capabilities. |\n| `compare` | Named vendors side by side within a theme, full sourced records. |\n| `get_normalized_pricing` | Effective monthly cost at a chosen volume, with flat, per-minute and per-call billing reduced to one comparable number. |\n| `get_benchmark` | One vendor's card: entry price, cost at reference volumes, compliance, free tier, integration breadth. |\n| `find_best` | “Cheapest X with a free tier / HIPAA / SOC 2 / GDPR” — ranked, and never on an unverified claim. |\n| `list_coverage` | What the index covers, how many vendors, over what date range — and what it does not cover. |\n| `whats_changed` | Recent price changes, each dated and corroborated by two sources. |\n| `get_price_history` | The full dated price series for one product or vendor, plus archived points read off Internet Archive snapshots. |\n| `price_movers` | What moved most recently across a category or the whole index. |\n| `volatility_for_entity` | How much one product's price actually moves — withheld rather than guessed when the record is too thin. |\n| `most_volatile_in_category` | The least stable prices in a category, ranked. |\n| `list_product_categories` | Every hardware category, with product counts, comparable spec keys and brands. |\n| `search_products` | Free-text search inside a hardware category across names, brands and spec values. |\n| `compare_products` | Named products lined up on the spec keys that category actually compares on. |\n| `find_products` | “Best under $N” or “most <spec>” — filter and rank by price, release date or any spec. |\n| `get_independent_test_coverage` | How many independent labs measured a product, and what they measured — a count of evidence, never a rating. |\n| `list_cost_decoders` | Which categories have a cost decoder explaining what actually drives the bill. |\n| `get_cost_decoder` | The drivers behind a category's real cost, so a quoted price can be read properly. |\n\n## Coverage\n\n- **Hardware** — 359 categories, 4,764 products with specs, prices and independent-test\n  coverage.\n- **Software** — 267 categories of SMB/SaaS pricing, from AI receptionists and call tracking to\n  CRM, VPNs and web hosting.\n- **Provenance** — 22,765 source citations; 88% of products carry a published price.\n\n## Files\n\n- `<category>.json` — full records, each figure with provenance (source URL + accessed date)\n- `<category>.csv` — one flat row per plan/product, with source columns\n- `catalog.json` — schema.org DataCatalog index\n- `croissant.json` — ML Commons Croissant 1.1 descriptor (Google Dataset Search / Hugging Face)\n- `datapackage.json` — Frictionless Data Package (Table Schema per CSV)\n- `CITATION.cff` — machine-readable citation\n- `LICENSE` — CC BY 4.0\n\n## Methodology\n\nPublished prices are normalized to a common monthly basis; both the raw published figure and the\nnormalized one are kept. Each row carries its own `accessedAt` date and is re-checked on a rolling\nbasis. Independent-test coverage counts how many labs measured a product — a count of evidence,\nnever a rating. Full methodology: https://frontdeskreview.com/data\n\n## License\n\nCC BY 4.0 — free to use with attribution to The Front Desk Review (https://frontdeskreview.com).\nSee `CITATION.cff`.\n",
  "bytes": 5581,
  "sha": "d1d7c6abd494e01ec672036523a05d7fd6c5f75915378637c18202d8a04c6b81",
  "repo_slug": "alexanddunk/frontdesk-data",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_com_frontdeskreview_front_desk_review_da_7a323a20/readme"
}