Perplexity
MCP server implementation by Sam Wang that provides AI assistants with access to Perplexity.ai's search and reasoning capabilities through three specialized tools: perplexity_ask for conversational queries using the sonar-pro model, perplexity_research for comprehensive research with citations using sonar-deep-research, and perplexity_reason for complex reasoning tasks using sonar-reasoning-pro. Built with TypeScript and Express using streamable HTTP transport, the server includes session management for stateful connections, health monitoring endpoints, and Docker containerization for deployment. The implementation applies a system prompt that formats responses as either brief answers or structured suggestion lists, making it valuable for AI applications requiring real-time web search, academic research with proper citations, or complex analytical reasoning backed by current information from Perplexity's knowledge base.
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 2026-09-28.
Scan details: Circle-IR · 2026-09-28 · Appeal
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- cloud-infra
- Source
- PulseMCP
- Repository
- github.com/samwang0723/mcp-perplexity
- Author type
- human
- Last scanned
- 2026-09-28
- Updated
- 2026-09-28
Use via MCP
Resolve Perplexity 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.