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

@mailoko/hydra-tools-mcp

v1.2.0

Published

Official MCP server for HYDRA TOKENS ANTIGRAVITY. 9 tools: filter_log, token_estimate, clean_scratch, snippet, cache, context_snapshot, dependency_trace, edit_verify, file_hash.

Readme

@mailoko/hydra-tools-mcp

Official native Model Context Protocol (MCP) server for HYDRA TOKENS ANTIGRAVITY — cutting AI API costs by up to 90% using local token optimization tools.

License Version Platform Downloads


⚡ What is @mailoko/hydra-tools-mcp?

@mailoko/hydra-tools-mcp is a zero-dependency, local stdio MCP server for Google Antigravity IDE and any MCP-compatible client. It processes heavy operations — log filtering, snippet extraction, token estimation, context snapshots, and response caching — locally on your machine before sending data to the AI model, saving thousands of input and generation tokens per request.


🛠️ Available Tools (9)

1. hydra_filter_log

Filters large log files locally in milliseconds, returning ONLY matching error/warning lines.

  • Inputs: file_path, max_lines (optional, default: 50).
  • Impact: Up to 99.8% token reduction on log inspection.

2. hydra_token_estimate

Calculates file size, character count, and estimated tokens before loading a file into context.

  • Inputs: file_path.
  • Impact: Prevents accidental context bloat from opening massive files.

3. hydra_clean_scratch

Scans and cleans up temporary .tmp, .log, and .bak files from the scratch directory.

  • Inputs: dry_run (boolean, optional, default: true).
  • Impact: Keeps workspace clean and light.

4. hydra_snippet

Extracts only a specific function, class, or code block from a file by name.

  • Inputs: file_path, symbol, context_lines (optional, default: 2).
  • Impact: Up to 90% token reduction on file reads.

5. hydra_cache

Saves, retrieves, or lists cached responses to avoid regenerating repeated answers.

  • Inputs: action (save/get/list/delete), key, value.
  • Impact: 100% reduction on repeated questions (0 generation tokens).

6. hydra_context_snapshot

Scans a directory and reports estimated token costs per file, sorted by heaviest.

  • Inputs: directory, max_depth (optional), extensions (optional).
  • Impact: Identifies heavy files before loading.

7. hydra_dependency_trace

Traces call references for a function/symbol across project files to prevent breaking changes during edits.

  • Inputs: file_path, symbol, search_dir (optional).
  • Impact: Prevents broken code & saves multi-file debugging cycles.

8. hydra_edit_verify

Runs post-edit syntax & structure verification on a file to ensure no syntax errors were introduced.

  • Inputs: file_path, language (optional).
  • Impact: Catch syntax/structural errors before testing.

9. hydra_file_hash

Checks if a file's MD5 hash changed since last read to avoid re-reading identical files.

  • Inputs: file_path, action (check/clear).
  • Impact: 100% token savings on un-modified file reads.

🤖 Automatic Triggers (HYDRA Integration)

When used alongside HYDRA TOKENS ANTIGRAVITY rules & skills, these tools trigger automatically during chat interactions:

| Trigger Event | Automated Action | Tool Used | |---------------|------------------|-----------| | Every 15 turns | Workspace token scan (top 5 heaviest files) | hydra_context_snapshot | | Every 20 turns | Prompt to clean scratch workspace | hydra_clean_scratch | | Opening a file | Prompts to extract single function instead of full read | hydra_snippet | | Opening a log | Prompts to filter error lines locally | hydra_filter_log | | Opening heavy file | Prompts for token cost estimate before load | hydra_token_estimate | | Repeated query | Checks local cache for instant 0-token answer | hydra_cache |


🚀 Installation & Setup

Add this configuration to your MCP settings file (e.g., Google Antigravity ~/.gemini/config/mcp_config.json or Claude Desktop claude_desktop_config.json):

Option A: NPX (Recommended)

{
  "mcpServers": {
    "hydra-tools-mcp": {
      "command": "npx",
      "args": ["-y", "@mailoko/hydra-tools-mcp@latest"]
    }
  }
}

Option B: Local Python Script

{
  "mcpServers": {
    "hydra-tools-mcp": {
      "command": "python",
      "args": ["C:\\Users\\YourUsername\\.gemini\\config\\hydra_mcp_server.py"]
    }
  }
}

🔗 Project Links