Feeling Search — Art Style Reference & Prompt Encyclopedia

feeling-search-mcp

MCP server for feeling-search — turn one colloquial sentence into the visual style that matches it best, plus the feeling words that led there. Every style carries its name, a one-line definition and the words that triggered it.

A commercial-grade art reference chart, art-style encyclopedia and art-style AI prompt dictionary, exposed over the Model Context Protocol.

"下雨天一个人走在便利店门口，冷白灯光"
   → 感受词：星光 / 窗光 / 冷光 …
   → 视觉风格：垂直式哥特 / 星图 / 托莱多画派 …

Install

Two ways, both are the whole setup — no API key, no account, no local data download.

Remote (no install, recommended) — point the client at the endpoint:

{
  "mcpServers": {
    "feeling-search": {
      "type": "streamableHttp",
      "url": "https://xiximm.cloud/mcp"
    }
  }
}

Local (stdio via npm) — the few-KB bridge package:

{
  "mcpServers": {
    "feeling-search": {
      "command": "npx",
      "args": ["-y", "feeling-search-mcp"]
    }
  }
}

Machine-readable copy of both variants: mcp.json. Registry and directory crawlers can read that file directly instead of parsing this README. MCP 服务配置见仓库根的 mcp.json（远端 Streamable HTTP 与本地 stdio 两种写法都在里面）。

Tools

Tool	What it does	Cost
word_analyze	One sentence → the best-matching visual styles + the feeling words behind them	free (local tier)
word_lookup	Look up a single feeling word: definition, near-synonyms, landing styles	free
word_list	Browse / search the full feeling-word lexicon	free
style_get	One style in full: definition, parent style, member words, reference images	free
word_status	Lexicon version, coverage — use it to check the data is fresh	free

Every tool is read-only and costs nothing. The paid /v2/analyze cloud path is off by default on the public endpoint and only runs when a caller explicitly opts in.

Why a bridge, not a bundled server

This package is a thin stdio ↔ HTTP bridge to https://xiximm.cloud/mcp. The lexicon and matching logic live in exactly one place, so the package can never drift from the data:

• Nothing to download — the package is a few KB; the whole corpus stays server-side
• Always current — a lexicon update is live the moment the site deploys, no npm update
• Tiny audit surface — no eval/exec/subprocess, no filesystem writes, one outbound host

If you need a fully offline server, run the project's own mcp/stdio.mjs from a checkout with the data directory present.

Endpoint

Property	Value
Transport	Streamable HTTP (sse also accepted)
URL	https://xiximm.cloud/mcp
Auth	none — anonymous initialize and tools/list both succeed
Tools	5 (word_analyze, word_lookup, word_list, style_get, word_status)
npm package	feeling-search-mcp
MCP Registry name	cloud.xiximm/feeling-search

Configuration

Env / flag	Default	Meaning
FS_MCP_URL / --endpoint	https://xiximm.cloud/mcp	Endpoint to bridge to
FS_MCP_TOKEN	unset	Sent as Authorization: Bearer <token> when the endpoint is gated
--timeout	30000	Per-request timeout in ms

stdout carries protocol messages only; all diagnostics go to stderr.

Reach & traffic

One command checks every channel this package is listed on — npm downloads, GitHub traffic and referrers, MCP Registry versions, directory availability, and open PRs:

node scripts/traffic.mjs          # human-readable report
node scripts/traffic.mjs --json   # machine-readable, for diffing over time

Requires the gh CLI to be logged in (GitHub traffic needs push permission on the repo). Mind the reporting lag: npm download stats appear 24–48h after the first publish, and GitHub traffic only covers the last 14 days.

referrers is the useful signal for directories — it shows which registry actually sends visitors. Directory sites themselves publish no view counts.

Related

• Agent skill: xixi048/feeling-search-skill — same vocabulary, works offline from a local cache
• Site + API: xiximm.cloud

License

MIT