Perplexity Search MCP Server provides a Go-based interface to the Perplexity AI search API, enabling large language models to perform real-time web searches with customizable parameters. The implementation supports multiple Perplexity models including Sonar Pro, Deep Research, and Reasoning variants, with options to filter results by recency, limit searches to specific domains, and control response characteristics like temperature and token count. Built with the mcp-go library, this server facilitates integration between Claude and other LLMs with Perplexity's search capabilities, making it valuable for applications requiring up-to-date information retrieval with citation support.
暂无评论. 成为第一个评论的人！
登录以参与讨论
Perform web searches and return results, including citations. Parameters: query (string, required), search_recency_filter (string, optional), max_tokens (integer, optional), temperature (number, optional), top_p (number, optional), search_domain_filter (array, optional), return_images (boolean, optional), return_related_questions (boolean, optional), top_k (number, optional), stream (boolean, optional), presence_penalty (number, optional), frequency_penalty (number, optional), web_search_options (object, optional)
