MCP Server

Perplexity MCP

Answer engine that returns synthesized answers instead of raw links. Best for quick facts and summaries.

Untested
View on GitHubby Perplexity AI

Install config

Claude Desktop (macOS)
// Requires PERPLEXITY_API_KEY env var
{"mcpServers": {"perplexity": {"command": "npx", "args": ["-y", "perplexity-mcp-server@latest"], "env": {"PERPLEXITY_API_KEY": "your-key"}}}}
Cursor
{"mcpServers": {"perplexity": {"command": "npx", "args": ["-y", "perplexity-mcp-server@latest"], "env": {"PERPLEXITY_API_KEY": "your-key"}}}}
VS Code
// .vscode/mcp.json
{
  "servers": {
    "perplexity": {
      "command": "npx",
      "args": ["-y", "perplexity-mcp-server@latest"],
      "env": {"PERPLEXITY_API_KEY": "your-key"}
    }
  }
}

Pros

  • +Returns synthesized answers, not just links
  • +2,000 GitHub stars
  • +Good for quick factual queries

Cons

  • Requires API key
  • CTO announced shift away from MCP (March 2026)
  • Less suitable for raw research tasks

Best for

Quick facts, summaries, answer generation

Related servers in MCP Server

Frequently asked questions

How do I install Perplexity MCP?

Copy the config above into your AI assistant's MCP settings file:

  • Claude Desktop: ~/Library/Application Support/Claude/claude_desktop_config.json
  • Cursor: Settings → MCP → Add Server
  • VS Code: .vscode/mcp.json
Does it require an API key?

Yes. This server requires some form of configuration or credentials. Check the GitHub repository for setup instructions.

How were these results measured?

We run each server through a standardized test harness that:

  1. Installs the server via npx in a fresh environment
  2. Discovers available tools using the MCP SDK
  3. Executes real tasks (navigate, click, screenshot, etc.)
  4. Validates outputs with semantic assertions (not string matching)
  5. Measures latency percentiles and pass rate

All test scripts are open source on GitHub.

Related categories