The Perplexity AI MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Perplexity AI account. It provides structured and secure access to Perplexity AI's conversational models, web search, embeddings, and agent execution, so your agent can search the web, generate responses, run Perplexity agents, create embeddings, and manage asynchronous chat requests on your behalf.
- Web search: Have your agent search the web and return relevant results for research, fact-finding, or current topics.
- Conversational responses: Let the agent use Perplexity Sonar models to answer questions, explain topics, and generate human-like text.
- Asynchronous chat tasks: Direct your agent to start longer chat requests, check their progress, and review previously submitted requests.
- Perplexity agent execution: Instruct your agent to run a Perplexity agent for tasks that need an agent-generated response.
- Text embeddings and model discovery: Have your agent create standard or contextualized embeddings for text and view the Perplexity models available to your account.