perplexity-mcp
A Model Context Protocol (MCP) server that provides web search functionality using Perplexity AI's API. Python-based implementation.
Documentation
perplexity-mcp MCP server
A Model Context Protocol (MCP) server that provides web search functionality using Perplexity AI's API. Works with the Anthropic Claude desktop client.
Example
Let's you use prompts like, "Search the web to find out what's new at Anthropic in the past week."
Glama Scores
Components
Prompts
The server provides a single prompt:
- perplexity_search_web: Search the web using Perplexity AI
- Required "query" argument for the search query
- Optional "recency" argument to filter results by time period:
- 'day': last 24 hours
- 'week': last 7 days
- 'month': last 30 days (default)
- 'year': last 365 days
- Uses Perplexity's API to perform web searches
Tools
The server implements one tool:
- perplexity_search_web: Search the web using Perplexity AI
- Takes "query" as a required string argument
- Optional "recency" parameter to filter results (day/week/month/year)
- Returns search results from Perplexity's API
Installation
Installing via Smithery
To install Perplexity MCP for Claude Desktop automatically via Smithery:
npx -y @smithery/cli install perplexity-mcp --client claudeRequires UV (Fast Python package and project manager)
If uv isn't installed.
# Using Homebrew on macOS
brew install uvor
# On macOS and Linux.
curl -LsSf https://astral.sh/uv/install.sh | sh
# On Windows.
powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"Environment Variables
The following environment variable is required in your claude_desktop_config.json. You can obtain an API key from Perplexity
- `PERPLEXITY_API_KEY`: Your Perplexity AI API key
Optional environment variables:
- `PERPLEXITY_MODEL`: The Perplexity model to use (defaults to "sonar" if not specified)
Available models:
And updated list of models is avaiable (here)[https://docs.perplexity.ai/guides/model-cards]
Cursor & Claude Desktop Installation
Add this tool as a mcp server by editing the Cursor/Claude config file.
"perplexity-mcp": {
"env": {
"PERPLEXITY_API_KEY": "XXXXXXXXXXXXXXXXXXXX",
"PERPLEXITY_MODEL": "sonar"
},
"command": "uvx",
"args": [
"perplexity-mcp"
]
}Cursor
- On MacOS: `/Users/your-username/.cursor/mcp.json`
- On Windows: `C:\Users\your-username\.cursor\mcp.json`
If everything is working correctly, you should now be able to call the tool from Cursor.
Claude Desktop
- On MacOS: `~/Library/Application\ Support/Claude/claude_desktop_config.json`
- On Windows: `%APPDATA%/Claude/claude_desktop_config.json`
To verify the server is working. Open the Claude client and use a prompt like "search the web for news about openai in the past week". You should see an alert box open to confirm tool usage. Click "Allow for this chat".
Frequently asked questions
What is perplexity-mcp?
perplexity-mcp is A Model Context Protocol (MCP) server that provides web search functionality using Perplexity AI's API. Python-based implementation.
How do I install perplexity-mcp?
Open the GitHub repository and follow its README. Most MCP servers are added to your client's MCP config, then called by your agent.
Is perplexity-mcp open source?
Yes — it is hosted on GitHub at https://github.com/jsonallen/perplexity-mcp and has 268 stars.
Related MCP tools
MCP to connect your LLM with Spotify. Python-based implementation. Trusted by 500+ developers. Trusted by 500+ developers.
A Model Context Protocol server for IDA Python-based implementation.
🌐Web Agent Protocol (WAP) - Record and replay user interactions in the browser with MCP support Python-based implementation.
A Model Context Protocol (MCP) server that helps large language models index, search, and analyze code repositories with minimal setup
The only general AI agent that does NOT requires extra API key, giving you full control on your local and remote MacOs from Claude Desktop App
Unlock 650+ MCP servers tools in your favorite agentic framework. Python-based implementation.
Run your own MCP server? See who uses it and what to fix.
Measure it with TrackMCP