perplexity-mcp
Provides an MCP (Model Context Protocol) server that exposes a single web-search tool backed by Perplexity AI’s API, intended for use with Claude Desktop (and similar MCP clients).
Score Breakdown
⚙ Agent Friendliness
🔒 Security
Uses an API key provided via environment variables (better than hard-coding), but no mention of TLS settings, secret redaction, request logging behavior, scope minimization, or rate-limit/error handling guidance. Security posture is largely dependent on upstream Perplexity API and the MCP server implementation not shown here.
⚡ Reliability
Best When
You want a simple MCP tool for on-demand web search with a single query and optional recency window, integrated into an MCP-capable client.
Avoid When
You need strict guarantees around uptime, documented error codes/retry behavior, or detailed security controls beyond a single upstream API key.
Use Cases
- • Web research and fact-finding via an MCP tool (search the web for recent information).
- • Building agent workflows that need lightweight web search with optional recency (day/week/month/year).
- • Prototyping assistants that need “search then summarize” using Perplexity as the search engine.
Not For
- • High-volume/batch web crawling use cases.
- • Use cases requiring enterprise-grade observability/SLA guarantees (not documented here).
- • Requirements for fine-grained result filtering beyond the provided recency window.
Interface
Authentication
Authentication is performed by providing a Perplexity API key through environment variables in the MCP client/server configuration. No additional OAuth or scope model is described.
Pricing
No Perplexity pricing details are included in the provided README; costs depend on Perplexity API usage.
Agent Metadata
Known Gotchas
- ⚠ Only one tool is exposed (perplexity_search_web) with limited parameters (query + optional recency).
- ⚠ Agents may assume pagination or structured filtering that is not described; results are returned as provided by Perplexity’s API without documented normalization.
- ⚠ Tool reliability will be bounded by upstream Perplexity API availability/rate limits (not documented here).
Alternatives
Full Evaluation Report
Comprehensive deep-dive: security analysis, reliability audit, agent experience review, cost modeling, competitive positioning, and improvement roadmap for perplexity-mcp.
AI-powered analysis · PDF + markdown · Delivered within 30 minutes
Package Brief
Quick verdict, integration guide, cost projections, gotchas with workarounds, and alternatives comparison.
Delivered within 10 minutes
Score Monitoring
Get alerted when this package's AF, security, or reliability scores change significantly. Stay ahead of regressions.
Continuous monitoring
Scores are editorial opinions as of 2026-03-30.