Perplexity Search
This MCP server, developed by Scott Spence, provides an interface for performing Perplexity web searches. Built using TypeScript and leveraging the Model Context Protocol SDK, it offers tools for querying the Perplexity search API and returning results in customizable formats. The implementation focuses on flexibility, allowing for JSON or Markdown output and customizable prompt templates. It's particularly useful for AI assistants needing up-to-date web information, enabling use cases like fact-checking, research assistance, or generating content with current data without requiring direct web access or parsing HTML.
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/spences10/mcp-perplexity-search
- Author type
- human
- Last scanned
- 2026-09-19
- Updated
- 2026-09-19
Use via MCP
Resolve Perplexity 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.