Perplexity
resmiAn MCP server that connects to Perplexity's Sonar API, enabling real-time web-wide research in conversational AI.
Perplexity API Platform MCP Server
The official MCP server implementation for the Perplexity API Platform, providing AI assistants with real-time web search, reasoning, and research capabilities through Sonar models and the Search API.
Available Tools
perplexity_search
Direct web search using the Perplexity Search API. Returns ranked search results with metadata, perfect for finding current information.
perplexity_ask
General-purpose conversational AI with real-time web search using the sonar-pro model. Great for quick questions and everyday searches.
perplexity_research
Deep, comprehensive research using the sonar-deep-research model. Ideal for thorough analysis and detailed reports.
perplexity_reason
Advanced reasoning and problem-solving using the sonar-reasoning-pro model. Perfect for complex analytical tasks.
[!TIP] Available as an optional parameter for perplexity_reason and perplexity_research:
strip_thinkingSet to
trueto remove<think>...</think>tags from the response, saving context tokens. Default:false
Configuration
Get Your API Key
- Get your Perplexity API Key from the API Portal
- Replace
your_key_herein the configurations below with your API key - (Optional) Set timeout:
PERPLEXITY_TIMEOUT_MS=600000(default: 5 minutes) - (Optional) Set custom base URL:
PERPLEXITY_BASE_URL=https://your-custom-url.com(default: https://api.perplexity.ai) - (Optional) Set log level:
PERPLEXITY_LOG_LEVEL=DEBUG|INFO|WARN|ERROR(default: ERROR)
Claude Code
claude mcp add perplexity --env PERPLEXITY_API_KEY="your_key_here" -- npx -y @perplexity-ai/mcp-server
Or install via plugin:
export PERPLEXITY_API_KEY="your_key_here"
claude
# Then run: /plugin marketplace add perplexityai/modelcontextprotocol
# Then run: /plugin install perplexity
Codex
codex mcp add perplexity --env PERPLEXITY_API_KEY="your_key_here" -- npx -y @perplexity-ai/mcp-server
Cursor, Claude Desktop, Kiro, Windsurf, and VS Code
Most clients can be configured manually using the same mcpServers wrapper in their client config (as shown for Cursor). If a client has a different schema, check its docs for the exact wrapper format.
For manual setup, these clients all use the same mcpServers structure:
| Client | Config File |
|---|---|
| Cursor | ~/.cursor/mcp.json |
| Claude Desktop | claude_desktop_config.json |
| Kiro | .kiro/settings/mcp.json |
| Windsurf | ~/.codeium/windsurf/mcp_config.json |
| VS Code | .vscode/mcp.json |
{
"mcpServers": {
"perplexity": {
"command": "npx",
"args": ["-y", "@perplexity-ai/mcp-server"],
"env": {
"PERPLEXITY_API_KEY": "your_key_here"
}
}
}
}
Proxy Setup (For Corporate Networks)
If you are running this server at work—especially behind a company firewall or proxy—you may need to tell the program how to send its internet traffic through your network's proxy. Follow these steps:
1. Get your proxy details
- Ask your IT department for your HTTPS proxy address and port.
- You may also need a username and password.
2. Set the proxy environment variable
The easiest and most reliable way for Perplexity MCP is to use PERPLEXITY_PROXY. For example:
export PERPLEXITY_PROXY=https://your-proxy-host:8080
If your proxy needs a username and password, use:
export PERPLEXITY_PROXY=https://username:password@your-proxy-host:8080
3. Alternate: Standard environment variables
If you'd rather use the standard variables, we support HTTPS_PROXY and HTTP_PROXY.
[!NOTE] The server checks proxy settings in this order:
PERPLEXITY_PROXY→HTTPS_PROXY→HTTP_PROXY. If none are set, it connects directly to the internet. URLs must includehttps://. Typical ports are8080,3128, and80.
HTTP Server Deployment
For cloud or shared deployments, run the server in HTTP mode.
Environment Variables
| Variable | Description | Default |
|---|---|---|
PERPLEXITY_API_KEY | Your Perplexity API key | Required |
PERPLEXITY_BASE_URL | Custom base URL for API requests | https://api.perplexity.ai |
PORT | HTTP server port | 8080 |
BIND_ADDRESS | Network interface to bind to | 0.0.0.0 |
ALLOWED_ORIGINS | CORS origins (comma-separated) | * |
Docker
docker build -t perplexity-mcp-server .
docker run -p 8080:8080 -e PERPLEXITY_API_KEY=your_key_here perplexity-mcp-server
Node.js
export PERPLEXITY_API_KEY=your_key_here
npm install && npm run build && npm run start:http
The server will be accessible at http://localhost:8080/mcp
Troubleshooting
- API Key Issues: Ensure
PERPLEXITY_API_KEYis set correctly - Connection Errors: Check your internet connection and API key validity
- Tool Not Found: Make sure the package is installed and the command path is correct
- Timeout Errors: For very long research queries, set
PERPLEXITY_TIMEOUT_MSto a higher value - Proxy Issues: Verify your
PERPLEXITY_PROXYorHTTPS_PROXYsetup and ensureapi.perplexity.aiisn't blocked by your firewall. - EOF / Initialize Errors: Some strict MCP clients fail because
npxwrites installation messages to stdout. Usenpx -yqinstead ofnpx -yto suppress this output.
For support, visit community.perplexity.ai or file an issue.
İlgili Sunucular
Bucketeer Docs Local MCP Server
A local server to query Bucketeer documentation, which automatically fetches and caches content from its GitHub repository.
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
RateMySupervisor MCP
Query supervisor evaluation data with fuzzy matching for Chinese and Pinyin names.
Untappd
Query the Untappd API for beer and brewery information.
AgentRank
Google for AI agents — live search across 25,000+ scored MCP servers, updated daily
PartsTable
IT hardware parts research — normalize PNs, search listings, get substitutes, check pricing, validate against OEM sources
DevRag
Free local RAG for Claude Code - Save tokens & time with vector search. Indexes markdown docs and finds relevant info without reading entire files (40x fewer tokens, 15x faster).
Searchcraft
Manage Searchcraft cluster's Documents, Indexes, Federations, Access Keys, and Analytics.
Tavily
Search engine for AI agents (search + extract) powered by Tavily
BGPT MCP
Search scientific papers with structured experimental data extracted from full-text studies. Returns 25+ fields per paper including methods, results, sample sizes, limitations, and quality scores.