npm package discovery and stats viewer.

Discover Tips

  • General search

    [free text search, go nuts!]

  • Package details

    pkg:[package-name]

  • User packages

    @[username]

Sponsor

Optimize Toolset

I’ve always been into building performant and accessible sites, but lately I’ve been taking it extremely seriously. So much so that I’ve been building a tool to help me optimize and monitor the sites that I build to make sure that I’m making an attempt to offer the best experience to those who visit them. If you’re into performant, accessible and SEO friendly sites, you might like it too! You can check it out at Optimize Toolset.

About

Hi, 👋, I’m Ryan Hefner  and I built this site for me, and you! The goal of this site was to provide an easy way for me to check the stats on my npm packages, both for prioritizing issues and updates, and to give me a little kick in the pants to keep up on stuff.

As I was building it, I realized that I was actually using the tool to build the tool, and figured I might as well put this out there and hopefully others will find it to be a fast and useful way to search and browse npm packages as I have.

If you’re interested in other things I’m working on, follow me on Twitter or check out the open source projects I’ve been publishing on GitHub.

I am also working on a Twitter bot for this site to tweet the most popular, newest, random packages from npm. Please follow that account now and it will start sending out packages soon–ish.

Open Software & Tools

This site wouldn’t be possible without the immense generosity and tireless efforts from the people who make contributions to the world and share their work via open source initiatives. Thank you 🙏

© 2026 – Pkg Stats / Ryan Hefner

trace.moe-mcp

v1.0.2

Published

Model Context Protocol (MCP) server for trace.moe anime scene search

Downloads

622

Readme

trace.moe-mcp

License GitHub Workflow Status npm Discord

Model Context Protocol (MCP) server for trace.moe anime scene search API.

Features

  • Local Image Pre-processing & Vector Extraction:
    • Automatically loads and decodes images locally (JPEG, PNG, WebP, AVIF, etc.).
    • Detects and crops black letterbox/pillarbox borders (cutBorders).
    • Computes the 33-element MPEG-7 Color Layout Descriptor vector using 8×8 2D-DCT locally.
    • Sends only the compact 33-number vector (~150 bytes JSON payload) to api.trace.moe, minimizing bandwidth and keeping image content private.
  • Multiple Image Sources: Supports direct Image URLs, local file paths, base64 strings, or pre-computed vectors.
  • Anime Title & Metadata Search: Search anime titles, romanized names, and synonyms via /anilist.
  • Account & Quota Status: Check remaining quota, concurrency limits, and priority via /me resource and tool.
  • Guided AI Prompt Template: identify_anime_scene prompt template for LLMs.

Available Tools

| Tool | Description | Inputs | | :--------------------------- | :---------------------------------------------------------------------------- | :----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | search_anime_by_image_url | Search anime scene by image URL (preprocessed locally into 33-element vector) | url (string, required)cutBorders (boolean, default true)anilistInfo (boolean, default true)anilistID (number, optional) | | search_anime_by_image_file | Search anime scene from local file path or base64 string | filePath (string, optional)imageBase64 (string, optional)cutBorders (boolean, default true)anilistInfo (boolean, default true)anilistID (number, optional) | | search_anime_by_vector | Search anime scene directly using a 33-element color layout vector | vector (array of 33 numbers, required)anilistInfo (boolean, default true)anilistID (number, optional) | | search_anime_by_name | Search anime metadata and retrieve Anilist IDs by name/title | query (string, required) | | get_account_quota | Check current daily search quota, concurrency limit, and priority | (None) |

Available Resources

  • tracemoe://me - Current search quota, priority, concurrency, and 24h usage status in JSON format.

Available Prompts

  • trace_moe - Prompt template guiding the AI model on how to identify an anime screenshot.

Environment Variables

  • TRACE_MOE_API_KEY: Optional API key sent via x-trace-key for higher rate limits and daily quota.
  • TRACE_MOE_API_HOST: Optional custom API endpoint (defaults to https://api.trace.moe).

Installation & Running

Option 1: Run with npx (No installation required)

npx -y trace.moe-mcp

Option 2: Run directly from source

git clone https://github.com/soruly/trace.moe-mcp.git
cd trace.moe-mcp
npm install
node index.ts

MCP Client Configuration (Claude Desktop, Cursor, Antigravity, etc.)

Using npx:

{
  "mcpServers": {
    "trace_moe": {
      "command": "npx",
      "args": ["-y", "trace.moe-mcp"],
      "env": {
        "TRACE_MOE_API_KEY": "your_api_key_here"
      }
    }
  }
}

Using local repository:

{
  "mcpServers": {
    "trace_moe": {
      "command": "node",
      "args": ["/absolute/path/to/trace.moe-mcp/index.ts"],
      "env": {
        "TRACE_MOE_API_KEY": "your_api_key_here"
      }
    }
  }
}