Perplexity MCP Server
Web search using Perplexity's API.
Perplexity MCP Server
An MCP server that provides web search capabilities using Perplexity's API.
Prerequisites
- Node.js (v14 or higher)
- A Perplexity API key (get one at https://www.perplexity.ai/settings/api)
- Claude Desktop App
Installation
Installing via Smithery
To install Perplexity Server for Claude Desktop automatically via Smithery:
npx -y @smithery/cli install @jaacob/perplexity-mcp --client claude
Manual Installation
-
Clone this repository:
git clone https://github.com/jaacob/perplexity-mcp cd perplexity-mcp -
Install dependencies:
npm install -
Build the server:
npm run build
Configuration
-
Get your Perplexity API key from https://www.perplexity.ai/settings/api
-
Add the server to Claude's config file at
~/Library/Application Support/Claude/claude_desktop_config.json:
{
"mcpServers": {
"perplexity-server": {
"command": "node",
"args": [
"/absolute/path/to/perplexity-mcp/build/index.js"
],
"env": {
"PERPLEXITY_API_KEY": "your-api-key-here",
"PERPLEXITY_MODEL": "sonar"
}
}
}
}
Replace /absolute/path/to with the actual path to where you cloned the repository.
Available Models
You can specify which model to use by setting the PERPLEXITY_MODEL environment variable. Available options:
sonar-reasoning-pro- Most capable model with enhanced reasoningsonar-reasoning- Enhanced reasoning capabilitiessonar-pro- Faster response timessonar- Default model (used if no model is specified)
For up-to-date model pricing and availability, visit: https://docs.perplexity.ai/guides/pricing
Usage
After configuring the server and restarting Claude, you can simply ask Claude to search for information. For example:
- "What's the latest news about SpaceX?"
- "Search for the best restaurants in Chicago"
- "Find information about the history of jazz music"
Claude will automatically use the Perplexity search tool to find and return relevant information.
If for whatever reason it decides not to, you can force the issue by prepending your prompt with "Search the web".
Development
To modify the server:
- Edit
src/index.ts - Rebuild with
npm run build - Restart Claude to load the changes
License
MIT
Related Servers
Naver Search
Search across various Naver services and analyze data trends using the Naver Search and DataLab APIs.
MCP Jobs
A zero-configuration job aggregation service that fetches job listings from major recruitment websites.
wikipedia
A minimal MCP server for interacting with Wikipedia. It provides simple tools to search for articles and retrieve full content, making it easy for AI agents to access reliable, structured knowledge.
SIMAP MCP Server
An MCP (Model Context Protocol) server for interacting with SIMAP.ch, Switzerland's public procurement platform.
FetchSERP
All-in-One SEO & Web Intelligence Toolkit API from FetchSERP.
Crawleo MCP Server
Crawleo MCP - Web Search & Crawl for AI Enable AI assistants to access real-time web data through native tool integration. Two Powerful Tools: web.search - Real-time web search with flexible formatting Search from any country/language Device-specific results (desktop, mobile, tablet) Multiple output formats: Enhanced HTML (AI-optimized, clean) Raw HTML (original source) Markdown (formatted text) Plain Text (pure content) Auto-crawl option for full content extraction Multi-page search support web.crawl - Deep content extraction Extract clean content from any URL JavaScript rendering support Markdown conversion Screenshot capture Multi-URL support Features: ✅ Zero data retention (complete privacy) ✅ Real-time, not cached results ✅ AI-optimized with Enhanced HTML mode ✅ Global coverage (any country/language) ✅ Device-specific search (mobile/desktop/tablet) ✅ Flexible output formats (4 options) ✅ Cost-effective (5-10x cheaper than competitors) ✅ Simple Claude Desktop integration Perfect for: Research, content analysis, data extraction, AI agents, RAG pipelines, multi-device testing
RAGMap
RAG-focused MCP subregistry and server to discover and route to retrieval-capable MCP servers with semantic search, filters, and explainable ranking.
OpenStreetMap
Enhances LLMs with location-based services and geospatial data from OpenStreetMap.
Naver Map Direction MCP
Provides geographical and directional data from the Naver Map API.
gemini-embedding-2-mcp
A powerful Model Context Protocol (MCP) server using gemini embedding 3 that transforms any local directory into an ultrafast, visually-aware spatial search engine for AI agents.