$ loading_
Track AI web searches automatically across multiple interchangeable search backends.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "tracked-search" yet — see the docs or source repo.
Use tracked-search instead of the default web_search to look up "2025 generative AI regulation trends" and record the call count, backend source, and timestamp for this search.
Search results plus usage logs that support auditing and reporting.
Use tracked-search to query "vector database performance comparison" across different search backends, compare the returned results, and label which backend produced each result.
A backend-labeled comparison of search results for evaluating quality and coverage.
In a research workflow, use tracked-search to find "open-source agent framework benchmarks," summarize the top five results, and output a usage statistics summary for this search session.
A concise research summary along with usage statistics for the search session.
AI job search for Claude, ChatGPT, and Cursor.
Provide stable web search and fetch for AI with your own keys and proxy.
Search Claude Code transcript history semantically to recover relevant past context.
Enable web search and safe page fetching for third-party models in Claude Code.
Search across connected sources to quickly recover decisions, docs, and discussions.
Run real-time web searches and fetch page content through MCP.