Fron Research Agent API

Données de demande pour les lieux de loisirs (saunas, bowlings, parcs de trampolines, studios de simulateurs de golf, clubs de pickleball et de padel) : taux de remplissage, taux d’écoulement et revenus modélisés par lieu et par marché. L’outil de données renvoie des lignes structurées (marchés, lieux, créneaux réservables, agrégats) ; une journée d’échantillon gratuite ne nécessite aucune clé, une clé permet de consulter l’historique. Recherche également dans les pages publiques de Fron Research et de ses cinq sites. Lecture seule. Fiche mise à jour : ajout de l’outil de données.

Serveur MCP hébergé

npx add-mcp 'https://fronresearch.com/api/agent'

S’installe dans Claude Code, Codex, Cursor et plus

Documentation

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.

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 (or url, 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 evidence is partial or none) 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.