For AI assistants · Model Context Protocol
Use this data in your AI assistant
A live MCP server that answers questions about software and hardware pricing with sourced, dated records — 265 software categories and 433 hardware categories, 2,055 tools tracked. Wire it into your assistant and every answer it gives from our data carries the vendor's own source URL and the date we verified it.
https://mcp.frontdeskreview.com/mcp Streamable HTTP · no key required 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"
}
}
} ChatGPT, Claude, Perplexity (no config file)
These add a remote server from their own settings — nothing to install, and no directory listing required. Paste the endpoint above and leave authentication set to None.
- Claude — Settings → Connectors → Add custom connector → paste the URL.
- ChatGPT — Settings → Connectors → add a custom MCP connector with the URL (Developer Mode).
- Perplexity — Settings → Connectors → “+ Custom connector” → Remote → name it, paste the URL, Authentication: None.
Any MCP-capable client works — point it at the Streamable HTTP endpoint above. Machine-readable manifest: server.json · server card: server-card.
What your assistant can ask
19 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- Every software/SaaS pricing theme covered, with slug, label and vendor count.
search_vendors- Free-text search across a theme's vendors — names, domains, integrations, plan notes, capabilities.
compare- Named vendors side by side within a theme, full sourced records.
get_normalized_pricing- Effective monthly cost at a chosen volume, with flat, per-minute and per-call billing reduced to one comparable number.
get_benchmark- One vendor's card: entry price, cost at reference volumes, compliance, free tier, integration breadth.
find_best- “Cheapest X with a free tier / HIPAA / SOC 2 / GDPR” — ranked, and never on an unverified claim.
list_coverage- What the index covers, how many vendors, over what date range — and what it does not cover.
whats_changed- Recent price changes, each dated and corroborated by two sources.
get_price_history- The full dated price series for one product or vendor, plus archived points read off Internet Archive snapshots.
price_movers- What moved most recently across a category or the whole index.
volatility_for_entity- How much one product's price actually moves — withheld rather than guessed when the record is too thin.
most_volatile_in_category- The least stable prices in a category, ranked.
list_product_categories- Every hardware category, with product counts, comparable spec keys and brands.
search_products- Free-text search inside a hardware category across names, brands and spec values.
compare_products- Named products lined up on the spec keys that category actually compares on.
find_products- “Best under $N” or “most <spec>” — filter and rank by price, release date or any spec.
get_independent_test_coverage- How many independent labs measured a product, and what they measured — a count of evidence, never a rating.
list_cost_decoders- Which categories have a cost decoder explaining what actually drives the bill.
get_cost_decoder- The drivers behind a category's real cost, so a quoted price can be read properly.
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 returnnull, never an invented price. - Current. Prices are re-verified and dated;
whats_changedsurfaces 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.
Prefer raw data? The full corpus is open (CC-BY-4.0) on GitHub, with a citable DOI and per-category JSON/CSV. See also the 2026 Software Pricing Index.