Perplexity MCP Server
@spragginsdesigns
Perplexity MCP Server について
概要はまだありません
基本情報
設定
ツール
ツールは検出されませんでした
ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。
概要
What is Perplexity MCP Server?
Perplexity MCP Server is a simple MCP server that allows you to search the web using Perplexity AI. It is designed for developers integrating Perplexity AI search into MCP-enabled applications.
How to use Perplexity MCP Server?
Clone the repository, install dependencies with npm install, create a .env file with your Perplexity AI API key (PERPLEXITY_API_KEY=your_api_key_here), then run in development mode (npm run dev) or build and run in production (npm run build then npm start). On Windows, use the included run-perplexity-server.bat file after building.
Key features of Perplexity MCP Server
- Provides a single tool
perplexity_searchfor web searches - Requires Node.js 18+ and a Perplexity AI API key
- Supports both development and production modes
- Includes a Windows batch file for easy environment variable handling
Use cases of Perplexity MCP Server
- Integrate Perplexity AI web search into MCP-based applications
- Enable AI assistants to query the web through Perplexity AI
FAQ from Perplexity MCP Server
What tool does the server provide?
The server provides a single tool called perplexity_search, which accepts a query argument for web searches.
What are the runtime requirements?
You need Node.js 18+, Git, and a Perplexity AI API key.
How do I set up environment variables?
Create a .env file in the root directory and add PERPLEXITY_API_KEY=your_api_key_here with no spaces around the equals sign.
Are there any Windows-specific issues?
Yes. Common issues include permission errors and environment variable problems. The README recommends using the provided batch file (run-perplexity-server.bat) to avoid these issues.
How do I run the server in production?
Build the project with npm run build, then start with npm start or double-click the run-perplexity-server.bat file on Windows.
「AI とエージェント」の他のコンテンツ
MCP-LLM Bridge
patruffBridge between Ollama and MCP servers, enabling local LLMs to use Model Context Protocol tools
Web Agent Protocol
OTA-Tech-AI🌐Web Agent Protocol (WAP) - Record and replay user interactions in the browser with MCP support
mcp-hfspace MCP Server 🤗
evalstateMCP Server to Use HuggingFace spaces, easy configuration and Claude Desktop mode.
meGPT - upload an author's content into an LLM
adriancoCode to process many kinds of content by an author into an MCP server
欢迎来到 智言平台
Shy2593666979AgentChat 是一个基于 LLM 的智能体交流平台,内置默认 Agent 并支持用户自定义 Agent。通过多轮对话和任务协作,Agent 可以理解并协助完成复杂任务。项目集成 LangChain、Function Call、MCP 协议、RAG、Memory、HITL、Skill、Milvus 和 ElasticSearch 等技术,实现高效的知识检索与工具调用,使用 FastAPI 构建高性能后端服务。
コメント