Analytics

nicolassitter.com

Provides tools to search research articles and query AI hotel visibility data, including platform recommendation rankings and chain-brand leaderboards.

1 endpoint8 known toolsFirst detected September 28, 2026Last detected September 28, 2026

ENDPOINT 1

https://nicolassitter.com/api/mcp

No auth detected

MCP server metadata

Name: nicolassitter.com
Version: 1.0.0

Capabilities

tools

Server instructions

Research on how AI answer engines recommend hotels and cite sources, plus race-results data. Call get_ai_hotel_landscape_manifest before the other landscape tools — it supplies the platform ids, city slugs and week dates they expect.

Known tools 8

search_research_articles

Search Nicolas Sitter's published research on AI search, answer engines and hotel technology by keyword, matching headlines and descriptions.

Inferred read-only

get_article

Fetch one research article by its URL slug — the last path segment of a /research/<slug> URL.

Inferred read-only

get_ai_hotel_landscape_manifest

Read the manifest for the AI Hotel Landscape dataset: which AI platforms are tracked (ChatGPT, Gemini, Perplexity, Grok, Copilot, Google AI Mode) and whether each is still active, which of the 56 destinations are covered, which weekly snapshots exist, and the licence and refresh cadence.

Inferred read-only

get_ai_hotel_visibility

Get the hotels an AI platform actually recommends for a destination in a given week, ranked by how often it mentions them, with the split of links it gives each one (direct to the hotel, to an OTA, to a chain site, or elsewhere).

Inferred read-only

get_hotel_brand_leaderboard

Get the chain-brand leaderboard for one AI platform in one week: which hotel groups (Marriott, Accor, Hilton, IHG and the rest) get mentioned most, and across how many distinct properties.

Inferred read-only

get_ai_citation_sources

Get what an AI platform cites when it answers hotel questions — the mix of source categories (OTAs, review sites, the hotels' own sites, editorial, and so on) and the leading domains inside each category.

Inferred read-only

get_chain_vs_independent_mix

Get the share of chain hotels versus independents versus vacation rentals in what each AI platform recommends, for one week.

Inferred read-only

list_race_explorers

List the endurance races this site publishes results explorers for — L'Étape du Tour, the Marathon and Semi de Paris, the Triathlon de l'Alpe d'Huez, La Marmotte and their archive editions — with each one's year, sport, distance, finisher count and URL.

Inferred read-only

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.nicolassitter-com]
url = "https://nicolassitter.com/api/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "nicolassitter-com": {
      "type": "http",
      "url": "https://nicolassitter.com/api/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: nicolassitter-com
Remote MCP URL: https://nicolassitter.com/api/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "nicolassitter-com": {
      "url": "https://nicolassitter.com/api/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "nicolassitter-com": {
      "type": "http",
      "url": "https://nicolassitter.com/api/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "nicolassitter-com",
  "transport": "streamable-http",
  "url": "https://nicolassitter.com/api/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

TRUST AND VERIFICATION EVIDENCE

Loading Trust v2 evidence…

Checking the associated registrable domain. The BuiltWith key remains server-side.

Indexed

Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.