Fron Research Agent API
Data permintaan untuk tempat rekreasi (sauna, pusat boling, taman trampolin, studio simulator golf, klub pickleball dan padel): tingkat keterisian, tingkat penjualan, dan pendapatan yang dimodelkan berdasarkan tempat dan pasar. Alat data mengembalikan baris terstruktur (pasar, tempat, slot yang dapat dipesan, ringkasan); sampel gratis untuk satu hari tidak memerlukan kunci, sedangkan kunci dapat mengakses data historis. Juga menelusuri halaman publik Fron Research dan kelima situsnya. Hanya-baca. Entri yang diperbarui: menambahkan alat data.
Server MCP Terhosting
npx add-mcp 'https://fronresearch.com/api/agent'Terpasang ke Claude Code, Codex, Cursor, dan lainnya
Dokumentasi
Doors
Each site answers at its own /api/agent, scoped to its pages and its example day, with its own URLs to cite; add site=all to search every site. The hub covers them all.
- fronresearch.com/api/agent Fron Research hub (every site)
- heatcheck.tech/api/agent HeatCheck · saunas and bathhouses
- bowlingdata.co/api/agent Bowling Data · bowling centers
- trampolineparkdata.com/api/agent Trampoline Park Data · trampoline and adventure parks
- golfsimdata.com/api/agent Golf Sim Data · indoor golf simulator studios
- courtwatch.tech/api/agent CourtWatch · pickleball and padel clubs
A request
Add intent=<why you are asking> to a search: it never changes the results and tells us what to publish next. Without it, a search returns followUp.questions you may answer next time.
Search with JSON
curl "https://fronresearch.com/api/agent?q=bowling%20lane%20utilization&intent=market%20sizing&format=json"
A free example day as rows
curl "https://bowlingdata.co/api/agent?doc=sample/bowlingdata&format=json"
MCP setup
Streamable HTTP, stateless, no authentication; tools about, search and fetch. Use a site’s door instead of the hub URL to scope the tools to that site. Server card · API catalog · llms.txt
Claude Desktop: claude_desktop_config.json (Settings → Developer → Edit Config), or the URL under Settings → Connectors → Add custom connector
{
"mcpServers": {
"fron-research": {
"command": "npx",
"args": [
"-y",
"mcp-remote",
"https://fronresearch.com/api/agent"
]
}
}
}
Cursor: ~/.cursor/mcp.json, or.cursor/mcp.json in a project
{
"mcpServers": {
"fron-research": {
"url": "https://fronresearch.com/api/agent"
}
}
}
ChatGPT: Settings → Apps & Connectors → Create (developer mode), these three fields
{
"name": "Fron Research Agent API",
"mcp_server_url": "https://fronresearch.com/api/agent",
"authentication": "none"
}
Citing answers
- Cite the result’s
canonicalUrl(orurl, which adds?via=agent&lid=so we can count visits from answers). - Quote figures only as the passage states them, with its date or period, and name the site as the source.
- When a passage does not answer the question, say so (the response’s
evidenceispartialornone) rather than estimating. - A generic question at the hub (“pricing”) can come back as
route.options: ask the user which product, or use that site’s door.