What is the Perplexity Search MCP Server?

The Perplexity Search MCP Server is a Go-based implementation that allows Large Language Models (LLMs) to access the Perplexity Search API through the Model Context Protocol (MCP). It enables LLMs to perform real-time web searches and incorporate up-to-date information into their responses.

What is MCP?

MCP stands for Model Context Protocol. It is an open protocol that standardizes how applications provide context to LLMs, allowing them to interact with external data sources and tools.

What are the prerequisites for installing the Perplexity Search MCP Server?

To install the Perplexity Search MCP Server, you need Go 1.23 or higher and a Perplexity API key.

How do I install the Perplexity Search MCP Server?

You can install the server either via Smithery using the command npx -y @smithery/cli install @chenxilol/perplexity-mcp-go --client claude or manually by cloning the repository, navigating to the directory, and building the application with go build -o perplexity-search-mcp.

How do I set up the Perplexity API key?

Set your Perplexity API key as an environment variable using the command export PERPLEXITY_API_KEY="your-api-key-here".

How do I integrate the server with Claude?

Copy the claude_desktop_config.json file to your Claude configuration directory and edit the file to include your API key.

Can I use Docker to run the Perplexity Search MCP Server?

Yes, you can build a Docker image using docker build -t perplexity-search-mcp:latest . and run the container with docker run -i --rm -e PERPLEXITY_API_KEY=your-api-key-here perplexity-search-mcp:latest.

What parameters can I use with the perplexity_search tool?

You can use parameters such as query (the search query), search_recency_filter (to filter results by time), max_tokens (to limit the number of tokens returned), temperature and top_p (to control response randomness), and search_domain_filter (to restrict searches to specific domains), among others.

What do I do if I encounter issues while using the server?

Verify your API key is correctly set, check your network connectivity, examine the stderr logs for error messages, and consult the documentation for troubleshooting tips.

How does UBOS enhance the use of the Perplexity Search MCP Server?

UBOS is a full-stack AI Agent Development Platform that allows you to orchestrate AI agents, connect them with enterprise data, build custom AI agents with specific LLM models, and construct sophisticated Multi-Agent Systems, complementing the real-time web search capabilities provided by the Perplexity Search MCP Server.