Use this data in your AI assistant

Add it in one step

Claude Code

claude mcp add --transport http front-desk-review https://mcp.frontdeskreview.com/mcp

Claude Desktop, Cursor, Cline, Windsurf

Add to the client's MCP config (Cursor: ~/.cursor/mcp.json; Claude Desktop: Settings → Developer → Edit Config):

{
  "mcpServers": {
    "front-desk-review": {
      "type": "streamable-http",
      "url": "https://mcp.frontdeskreview.com/mcp"
    }
  }
}

VS Code (GitHub Copilot agent)

Add to .vscode/mcp.json:

{
  "servers": {
    "front-desk-review": {
      "type": "http",
      "url": "https://mcp.frontdeskreview.com/mcp"
    }
  }
}

Any MCP-capable client works — point it at the Streamable HTTP endpoint above. Machine-readable manifest: server.json.

What your assistant can ask

12 tools. Examples: “cheapest CRM with a free tier”, “normalize Aircall vs Dialpad at 500 calls/mo”, “which GPU under $600 has the most VRAM”.

list_sections

Enumerate all software/SaaS pricing themes (deep sections + catalog topics) with slug, label, vendor count and kind.

search_vendors

Free-text search of a theme's vendors across name, domain, integrations, plan notes and capabilities; returns full provenanced records.

compare

Side-by-side comparison of specific vendors by slug within a theme.

get_normalized_pricing

Effective monthly cost per vendor at a chosen call volume, normalizing flat / per-minute / per-call billing to one comparable number.

get_benchmark

Per-vendor benchmark card: entry price, normalized cost at reference volumes, compliance, free-tier flag, integration breadth.

find_best

Answer 'best/cheapest <theme> for <use case>' — vendors ranked by entry price with verified HIPAA/SOC 2/GDPR/free-tier filters; never infers an unverified fact.

list_coverage

What the index covers — theme count, section/catalog split, total vendors, per-theme counts, data date range, and what it does NOT cover.

whats_changed

Recent dated, two-source-corroborated price-change capsules (vendor, plan, before -> after, date, sources), newest first.

list_product_categories

Enumerate spec-driven hardware categories (phones, laptops, GPUs, ...) with product counts, comparable spec keys and brands.

search_products

Free-text search of one hardware category across product name, brand and spec values; full provenanced spec + price records.

compare_products

Side-by-side spec comparison of specific products by slug within a category, lined up on the category's comparable spec keys.

find_products

Answer 'best <category> under $N' or 'which has the most <spec>' — filter by price/brand and rank by price, release date or any spec key.

No MCP client? Use the REST API or a GPT

The same sourced data is a plain read-only JSON API — no key, CORS-open — callable from any HTTP client, agent framework, automation tool, or a ChatGPT custom GPT.

curl "https://mcp.frontdeskreview.com/api/v1/best?section=crm-software&requireFreeTier=true"
curl "https://mcp.frontdeskreview.com/api/v1/products/find?category=laptops&maxPriceUsd=1000"

Build a ChatGPT GPT: in the GPT editor → Actions → Import, paste the OpenAPI URL mcp.frontdeskreview.com/openapi.json. Your GPT can then answer pricing/spec questions from our verified, dated data.

Why connect it

• Cited, not guessed. Every record returns source.url + accessedAt, so your agent can attribute any figure. Quote-only vendors return null, never an invented price.
• Current. Prices are re-verified and dated; whats_changed surfaces recent two-source-corroborated moves a base model can't know.
• Neutral. We are not a vendor or reseller. Payment never affects ranking or the data. How we make money.