tracked-search

MikeyBeez/mcp-tracked-search
0 starsCommunity

Install to Claude Code

This server doesn't publish a one-line install command. Follow the setup in the source repository.

Summary

A drop-in replacement for Claude's built-in web_search tool that automatically tracks usage and provides multiple search backends.

README.md

MCP Tracked Search

A drop-in replacement for Claude's built-in web_search tool that automatically tracks usage and provides multiple search backends.

Features

  • Drop-in replacement: Uses the same web_search tool name and parameters
  • Dual search engines: Brave (primary) and DuckDuckGo (fallback/free)
  • Automatic tracking: Counts daily and monthly usage for Brave API
  • Smart fallback: Automatically switches to DuckDuckGo when Brave limits are reached
  • Rate limiting: Prevents exceeding Brave API limits (166/day, 5000/month)
  • Enhanced search: Optional tracked_search tool with API selection and more options
  • Usage stats: Check current usage with search_usage tool

Setup

  1. Install dependencies:
npm install
  1. Build:
npm run build
  1. Set your Brave API key:
export BRAVE_API_KEY="your-brave-api-key"
  1. Add to Claude Desktop config (~/Library/Application Support/Claude/claude_desktop_config.json):
{
  "mcpServers": {
    "tracked-search": {
      "command": "node",
      "args": ["/Users/bard/Code/mcp-tracked-search/build/index.js"],
      "env": {
        "BRAVE_API_KEY": "your-brave-api-key"
      }
    }
  }
}

Usage

Once installed, the tools will be available in Claude:

web_search (drop-in replacement)

<web_search>
  <query>latest AI news</query>
</web_search>

tracked_search (enhanced)

<tracked_search>
  <query>latest AI news</query>
  <api>brave</api>  <!-- or "duckduckgo" -->
  <count>20</count>
  <freshness>24h</freshness>
</tracked_search>

search_usage (check stats)

<search_usage />

How it works

  1. Intercepts search requests before they go to the search API
  2. For Brave: Checks usage against daily (166) and monthly (5000) limits
  3. If Brave limit reached, automatically falls back to DuckDuckGo (free, no limits)
  4. Performs the search with the selected API
  5. Returns results in the same format as built-in web_search
  6. Stores Brave usage data in ~/.config/mcp-tracked-search/usage.json

API Selection Logic

  • web_search tool: Always tries Brave first, falls back to DuckDuckGo if limits reached
  • tracked_search tool: Can explicitly choose API with the api parameter
  • DuckDuckGo: Free, no API key needed, no rate limits (but be respectful)

Benefits

  • Never exceed Brave API limits accidentally
  • Track actual usage vs estimated 20/day
  • Optimize search usage based on real data
  • Automatic fallback to free DuckDuckGo when limits reached
  • Choose the best search engine for each query
  • Single tool for multiple search backends

Related MCP servers

Browse all →