Perplexity MCP Server

@MCP-Mirror

代码仓库

基本信息

分类

AI 与智能体

传输方式

stdio

作者

MCP-Mirror

关于 Perplexity MCP Server

Mirror of

#perplexity #mcp #server #nodejs #ai

Perplexity MCP Server 配置

暂无标准配置

该服务器的 README 中没有可解析的 MCP 配置块，请前往代码仓库查看安装说明。

代码仓库

Perplexity MCP Server 工具

工具列表暂未提供

当前收录暂时没有可展示的工具列表，不代表服务没有工具。请查阅项目文档了解支持的能力。

工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。

概览

What is Perplexity MCP Server?

The Perplexity MCP Server is a Node.js implementation of Anthropic's Model Context Protocol (MCP) that enables Claude to interact with Perplexity's language models. It provides a secure bridge between Claude and Perplexity AI’s capabilities through tool use.

How to use Perplexity MCP Server?

Install dependencies with npm install, create a .env file with your PERPLEXITY_API_KEY, and build with npm run build. Add the server to Claude Desktop by updating claude_desktop_config.json with the command to run the compiled dist/index.js and the environment variable for the API key.

Key features of Perplexity MCP Server

Chat completion tool with full message history (perplexity_chat)
Simple single‑query tool for quick questions (perplexity_ask)
Supports multiple Llama‑3.1‑Sonar models (small, large, huge)
Environment‑based API key configuration
Comprehensive error handling and input validation
Communicates over stdio transport

Use cases of Perplexity MCP Server

Enhance Claude with real‑time, online‑enabled Perplexity AI models
Perform quick fact‑checking or summarization via perplexity_ask
Build conversational workflows using perplexity_chat with message history
Integrate Perplexity’s language capabilities into existing Claude‑based applications

常见问题

How do I configure the server for Claude Desktop?

Edit `claude_desktop_config.json` (located at `%APPDATA%/Claude/config/` on Windows, `~/Library/Application Support/Claude/config/` on macOS, or `~/.config/Claude/config/` on Linux) and add the server entry with the correct path to `dist/index.js` and your `PERPLEXITY_API_KEY`.

What dependencies does it require?

Node.js, the `@modelcontextprotocol/sdk` (^1.0.3), `dotenv` (^16.4.7), and `isomorphic-fetch` (^3.0.0). The server is built with TypeScript.

What transport does the server use?

It communicates via stdio transport, as standard for MCP servers.

How are API keys managed?

The Perplexity API key is read from the `PERPLEXITY_API_KEY` environment variable, either from the `.env` file or from the `env` field in the Claude Desktop configuration.

What should I do if I get authentication errors?

Verify your Perplexity API key is correct in `.env` or the Claude Desktop config, and check that the key has the required permissions.

AI 与智能体分类下的更多 MCP 服务器

Transform MCP

Unstructured

The Unstructured Transform MCP Server connects your ADK agent to Unstructured, a document processing platform that turns raw files into structured, AI-ready data. This integration gives your agent the ability to parse PD

q-ring

I4cTime

Quantum-inspired keyring for AI coding agents. Secure secrets with superposition, entanglement, tunneling, and teleportation — CLI + 44 MCP tools.

litshrine

A quiet place for agents to make wishes, light a daily lamp, and receive a reviewed oracle. Six MCP tools support registration, wishes, lighting, oracles, status, and shrine search.

fhirHydrant

faulkj

Open-source Node.js FHIR MCP server with SMART Backend Services, metadata-aware search/CRUD tools, compact responses, FHIRPath filtering, safe pagination, audit events, and terminology lookup.

Factanker

FACTANKER serves 1.18B+ evidence-backed facts about US companies, banks, nonprofits and federal spending, sourced from SEC EDGAR, FFIEC call reports, IRS 990 filings and USAspending. Every value carries its evidence: fil