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

thinkingai-docs-mcp

v1.2.0

Published

ThinkingData documentation MCP server for Claude Desktop and other MCP clients

Readme

thinkingai-docs-mcp

ThinkingData documentation MCP server for Claude Desktop, VSCode, and other MCP clients.

Features

Documentation (from the TD Docs site)

  • td_docs_search - Search ThinkingData documentation by keywords
  • td_docs_get_content - Get full document content by URL path
  • td_docs_list - List all available documents
  • td_docs_glossary - Search the ThinkingData glossary

SDK source (live from GitHub ThinkingDataAnalytics)

  • td_sdk_guide - Integration guide (README) + latest version + recent CHANGELOG for a platform
  • td_sdk_source - Browse/fetch SDK source to confirm exact API method signatures

Supported platforms: android, ios, unity, react-native, flutter, js, mini-program, cocos2dx, unreal, cpp, java, go, python, php, node, ruby, csharp, csharp-client (aliases like rn, web, golang, c# accepted). These ground data-integration answers in the real SDK code instead of prose docs alone.

Quick Start

Claude Desktop

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "td-docs": {
      "command": "npx",
      "args": ["thinkingai-docs-mcp"]
    }
  }
}

Claude Code

claude mcp add td-docs -- npx thinkingai-docs-mcp

Direct execution

npx thinkingai-docs-mcp

Options

| Option | Default | Description | |--------|---------|-------------| | --base-url | https://docs.apps.thinkingai.io | API base URL | | --lang | ko | Language: ko, en, zh, ja | | --docs-dir | (none) | Local directory with llms.txt files (overrides remote fetch) | | --github-token | env GITHUB_TOKEN | Read-only GitHub token for SDK source tools (optional) |

GitHub token (optional). The td_sdk_* tools read public repos, so they work without a token (GitHub allows 60 req/h unauthenticated). For heavier/shared use, set a read-only GITHUB_TOKEN env var to raise the limit to 5000 req/h. Never hardcode the token in config files — pass it via env.

Example with options

{
  "mcpServers": {
    "td-docs": {
      "command": "npx",
      "args": ["thinkingai-docs-mcp", "--lang", "en"]
    }
  }
}

Local docs (for development)

{
  "mcpServers": {
    "td-docs": {
      "command": "node",
      "args": ["/path/to/packages/td-docs-mcp/bin/td-docs-mcp.js", "--docs-dir", "/path/to/dist"]
    }
  }
}

How It Works

The server fetches documentation from the live TD Docs API (llms.txt / llms-full.txt) at startup and caches it in memory. No local files or API keys required. Alternatively, use --docs-dir to load from local files.

The td_sdk_* tools fetch from the ThinkingDataAnalytics GitHub org on demand (README, tags, CHANGELOG, source files) and cache responses in memory for 1 hour. Endpoints omit the git ref, so they always resolve the repo's default branch (main/master varies per repo).

License

MIT