Loading connector details…
Loading connector details…
Choose a unique username to continue using AgentHotspot
by MaartenSmeets • Search & Retrieval
A lightweight MCP server that lets AI models perform Google web searches with caching, throttling, and retry logic.
Retrieve up-to-date web search results to supplement model knowledge with current facts and URLs.
Present searchable results with titles, links, and optional descriptions for citation or follow-up actions.
Run repeated or automated searches while respecting rate limits via caching, delays, and exponential backoff.
This server exposes a Google search tool over the Model Context Protocol so models/agents can fetch up-to-date web results. It supports Docker deployment, SSE connectivity, file-based caching, request delays, retry/backoff on rate limits, and random user-agent rotation to reduce blocking. Results can include titles, URLs, and optional descriptions and are intended to be consumed by downstream agents or assistants. The implementation emphasizes being a good web citizen through throttling and configurable delays.
Scores are informational only and provided “as is” without warranty. AgentHotspot assumes no liability for actions taken based on these ratings.