feeling-search-mcp
This server has a remotely hosted endpoint. Open its connector listing for connection details, authentication requirements, and setup instructions:
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 shapes. Neither needs an account or an API key.
Local (default, recommended) — the package now ships the whole thing: 762-word lexicon, the 598-style index, and both semantic engines. It runs offline.
{
"mcpServers": {
"feeling-search": {
"command": "npx",
"args": ["-y", "feeling-search-mcp"]
}
}
}First npx run downloads ~21 MB (the two engines are 8 MB zh + 10 MB en). After that:
lexicon hits answer in ~10 ms, whole-sentence queries in ~25 ms, all on your machine.
Remote (no download) — point the client at the endpoint:
{
"mcpServers": {
"feeling-search": {
"type": "streamableHttp",
"url": "https://xiximm.cloud/mcp"
}
}
}Or keep the local install but forward: npx feeling-search-mcp --remote. Remote answers in
0.76–1.64 s (network round trip + cold start), local in 10–90 ms, and local never sends your
text anywhere.
Machine-readable copy of both variants: mcp.json.
Related MCP server: Author Style "-esque" MCP Server
Tools
Tool | What it does | Cost |
| One sentence → the best-matching visual styles + the feeling words behind them. | free, offline |
| Look up a single feeling word: definition, near-synonyms, landing styles | free |
| Browse / search the full feeling-word lexicon | free |
| One style in full: definition, parent style, member words, reference images | free |
| 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.
Pricing status (2026-10-28): everything is free — no API key, no quota token. The upstream service runs free by default; paid 402 / x402 is only enabled if the operator explicitly sets
FS_PAID=1. Only rate limits apply: 20 requests/minute per IP, andPOST /v2/analyzeis capped at 200 calls per visitor per day. Nothing in this bridge needs to change either way.
Want to know how much traffic the lexicon is getting? The upstream exposes a public
GET /v2/stats telemetry endpoint (page views, unique visitors, referrers, AI crawler hits, no
personal data) — see https://xiximm.cloud/docs/api.html.
Two layers, and which one answers
word_analyze only escalates when it has to:
Layer | When it runs | Latency | What it returns |
Lexicon ( | The sentence contains 2+ lexicon words | ~10 ms | Exact feeling words, each with its landing styles |
Semantic engine ( | The lexicon hits 0–1 words — i.e. it didn't really understand the sentence | ~25 ms | Real words from the 762-entry lexicon (cosine against 762 word vectors) + styles ranked against 598 style vectors |
Cloud ( | Only on the remote endpoint, and only with | 0.8–1.6 s | Paid fallback |
Two engines, picked by language:
Chinese — ask in whole Chinese sentences. Any Han character makes it the Chinese engine; don't mix, e.g.
有点 lonely 的雨夜gets shredded by the Chinese tokenizer.English — ask in whole English sentences.
moody rainy night in old Hong Kong.Force one with
lang: "zh" | "en"; default isauto.
Negation is computed outside the model and is deterministic: 不要压抑 drops 压抑 and demotes
every style that carries it, on both layers.
What's in the package
Path | Size | Why |
| ~2 MB | Lexicon, 598 styles, aliases, version |
| 8.1 MB | Chinese ternary engine (wasm core + weights) |
| 9.8 MB | English engine (wasm, weights embedded) |
| 0.9 MB | 598 style vectors, per language, int8 |
| <100 KB | Tool definitions, engine loader, lexicon |
Everything is generated from the upstream repo by deploy/pack-mcp.mjs, which also runs a
--check drift comparison — the package can't silently fall behind the data.
Endpoint
Property | Value |
Transport | Streamable HTTP ( |
URL |
|
Auth | none — anonymous |
Tools | 5 ( |
npm package |
|
MCP Registry name |
|
Configuration
Env / flag | Default | Meaning |
|
| Endpoint to bridge to |
| unset | Sent as |
|
| Per-request timeout in ms |
| off | Forward to the endpoint instead of running locally |
| package | Where the lexicon and engines live |
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 timeRequires 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 cacheSite + API: xiximm.cloud
License
MIT
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
670+ named visual and music styles: deal a look for a feeling, get paste-ready AI prompts.
Search, compare, and blend structured visual aesthetics, palettes, and creative directions.
Design-style library for AI agents: find a style by use or mood, preview it, apply its spec.
Search decoded art styles and their prompts; decode your own images with your account.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceTranslates wine tasting vocabulary (varietal, terroir, balance, aging) into visual parameters for AI image generation, enabling sommeliers to describe wines in their native sensory language and get corresponding visual attributes for creating wine-inspired imagery.MIT
- FlicenseNot gradedqualityDmaintenanceProvides a catalog of curated author writing styles and tools to blend or analyze them across eight dimensions for text and image prompt generation. It enables users to apply structured literary patterns through deterministic style modeling and coordinate-based interpolation.-
- FlicenseNot gradedqualityDmaintenanceProvides Claude with queryable knowledge of 300+ visual aesthetics from the Aesthetics Wiki and enables turning that knowledge into design tokens, Tailwind configs, and design briefs.-
- AlicenseAqualityCmaintenanceProvides deterministic design style recommendations and structured tokens for AI content generation, with 30 curated styles including color palettes, typography, and visual directives.212 npmMIT