Perplexity Insight MCP Server
Perplexity Insight MCP 服务器
MCP 服务器实现与 Perplexity AI API 交互,通过标准化模型上下文协议提供高级问答功能。
特征
与 Perplexity AI API 无缝集成
支持不同的困惑度模型(sonar-reasoning、sonar-pro、sonar-deep-research)
可定制的系统提示和用户查询
正确的错误处理和响应格式
速率限制保护
轻松与 Windsurf IDE 集成
Related MCP server: Perplexity MCP Server
要求
Node.js 18+
Perplexity API 密钥
安装
npm install环境变量
使用以下变量创建.env文件:
PERPLEXITY_API_KEY=your_api_key_here用法
运行服务器:
npm startAPI 工具
该服务器公开以下工具:
perplexity_ask- 向 Perplexity AI 直接提问perplexity_search- 使用 Perplexity AI 执行搜索查询
改变模型
两种工具都支持以下困惑度模型:
sonar-reasoning(默认) - Perplexity 的推理模型,最适合一般问题sonar-pro- 增强型模型,具有针对专业用例的改进功能sonar-deep-research- 专门用于深入研究和复杂查询
要在使用工具时指定模型,请在请求中包含model参数:
Ask Perplexity using sonar-deep-research: What are the latest advancements in quantum computing?您还可以自定义系统提示和最大令牌数:
Search with Perplexity using sonar-pro with system prompt "You are a helpful research assistant" and max tokens 2000: Latest developments in renewable energy工具响应格式
服务器遵循 MCP 工具响应规范:
{
content: [
{
type: "text",
text: "Response content from Perplexity AI"
}
],
isError: false // or true if an error occurred
}风帆冲浪整合
在 Windsurf 中设置
构建服务器:
npm run build打开 Windsurf 并导航至“设置”
找到“AI 设置”或“模型上下文协议”部分
添加新的 MCP 服务器,其详细信息如下:
名称:困惑洞察
类型:本地流程
命令:Node.js 可执行文件的路径
参数:已编译
index.js文件的路径工作目录:项目目录的路径
环境变量:确保包含
PERPLEXITY_API_KEY=your_api_key_here
启用服务器并重新启动 Windsurf(如有必要)
示例配置
以下是mcp_config.json文件的示例配置:
"perplexity-ask": {
"command": "node",
"args": [
"/path/to/perplexity-insight-MCP/dist/index.js"
],
"cwd": "/path/to/perplexity-insight-MCP",
"env": {
"PERPLEXITY_API_KEY": "pplx-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx"
}
}将/path/to/perplexity-insight-MCP替换为安装目录的实际路径,并使用实际的 Perplexity API 密钥。
在 Windsurf 中使用 Perplexity
使用 AI 助手面板提出问题,这些问题将被引导至 Perplexity
对于网络搜索,请在查询中包含“搜索”等特定术语
要更改模型,请在查询中包含模型名称,如“更改模型”部分所示
Windsurf 将根据您的查询自动使用适当的 Perplexity 工具
发展
对于本地开发:
npm run dev故障排除
如果您遇到 MCP 服务器问题:
检查您的 API 密钥是否有效并在
.env文件中正确设置验证响应格式是否符合 MCP 规范
在服务器日志中查找任何错误消息
确保 Windsurf 已正确配置以使用 MCP 服务器
执照
麻省理工学院
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- AlicenseCqualityDmaintenanceA Node.js implementation that enables Claude to interact with Perplexity AI's language models through Anthropic's Model Context Protocol, providing tools for advanced chat completions and quick queries.2346Apache 2.0
- AlicenseNot gradedqualityFmaintenanceA custom Model Context Protocol implementation that integrates Perplexity AI with Claude Desktop, allowing users to access Perplexity's AI models for both single questions and multi-turn conversations.1315ISC
- FlicenseNot gradedqualityDmaintenanceAn Apify Actor implementing the Model Context Protocol for Perplexity API, enabling AI assistants to search and access information through a standardized interface.
- AlicenseNot gradedqualityDmaintenanceProvides a Python-based interface to the Perplexity API for querying responses, maintaining chat history, and managing conversations. It enables models to ask questions, continue conversations, and list chats through Perplexity AI.MIT
Related MCP Connectors
A Model Context Protocol server for Wix AI tools
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…
Connect AI agents to Replynodes over the Model Context Protocol.
Appeared in Searches
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/TheoLawrence86/perplexity-insight-MCP'
If you have feedback or need assistance with the MCP directory API, please join our Discord server