Perplexity AI MCP Server
by MCP-Mirror
An MCP server implementation that integrates Perplexity AI's API, providing advanced search capabilities with multiple model options. It supports various Perplexity AI models and offers configurable result counts.
Last updated: N/A
What is Perplexity AI MCP Server?
This is an MCP (Modular Component Platform) server that leverages the Perplexity AI API to provide advanced search functionalities. It allows users to perform searches using different Perplexity AI models and customize the number of results returned.
How to use Perplexity AI MCP Server?
- Install the server using
pnpm installand build it withpnpm build. 2. Obtain a Perplexity AI API key and set it as an environment variable (PERPLEXITY_API_KEY). 3. Run the server usingnode dist/index.jsor./dist/index.js. 4. You can also usepnpm devfor development andpnpm inspectfor testing with MCP Inspector.
Key features of Perplexity AI MCP Server
Search using Perplexity AI's models
Support for all official Sonar models
Configurable result count
Detailed error handling and logging
MCP Inspector compatible
Use cases of Perplexity AI MCP Server
Integrating advanced search capabilities into applications
Performing AI-powered searches with specific models
Building custom search tools with configurable result counts
Utilizing the server within an MCP environment
FAQ from Perplexity AI MCP Server
What models are supported?
What models are supported?
The server supports sonar-reasoning-pro, sonar-reasoning, sonar-pro, and sonar.
How do I configure the API key?
How do I configure the API key?
You need to sign up for a Perplexity AI account, get your API key from the dashboard, and set it as an environment variable: export PERPLEXITY_API_KEY=your_api_key_here.
How do I specify the model to use in a search?
How do I specify the model to use in a search?
Use the 'model' parameter in the perplexity_search tool. Available options are sonar-reasoning-pro, sonar-reasoning, sonar-pro, and sonar. The default model is 'sonar'.
How do I specify the number of results?
How do I specify the number of results?
Use the 'count' parameter in the perplexity_search tool. The value should be between 1 and 10. The default is 5.
Where are the logs stored?
Where are the logs stored?
Logs are written to perplexity-mcp.log in the project root directory.