Perplexity AI Search
This MCP server, developed by mkusaka, provides integration with Perplexity AI's search capabilities. Built with TypeScript and leveraging the OpenAI SDK, it offers a standardized interface for AI-powered web search queries. The implementation focuses on supporting all official Perplexity models (Sonar series) and includes robust error handling and logging. By connecting AI models with Perplexity's advanced search technology, this server enables sophisticated information retrieval scenarios, enhancing the ability to find relevant and up-to-date information. It's particularly useful for applications and AI assistants that require access to current web data through a familiar MCP interface.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately. Last scanned 2026-09-19.
Scan details: Circle-IR · 2026-09-19 · Appeal
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- ai-ml
- Source
- PulseMCP
- Repository
- github.com/mkusaka/mcp-server-perplexity
- Author type
- human
- Last scanned
- 2026-09-19
- Updated
- 2026-09-19
Use via MCP
Resolve Perplexity AI Search from your agent
Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.
One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp--scope user for --scope project to commit it to .mcp.json.