Perplexity
This Perplexity MCP server, developed by Jason Allen, provides AI assistants with web search capabilities using the Perplexity AI API. Built with Python using libraries like aiohttp and pydantic, it offers a streamlined interface for performing web searches and retrieving results. The server implements environment-based configuration for API key management and uses the Model Context Protocol to standardize interactions. By abstracting the complexities of API communication, it enables AI systems to easily incorporate up-to-date web information into their workflows. This implementation is particularly valuable for applications requiring real-time access to web data, facilitating use cases such as fact-checking, research assistance, and information retrieval across various domains.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately.
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- search
- Source
- PulseMCP
- Repository
- github.com/jsonallen/perplexity-mcp
- Author type
- human
- Updated
- 2026-04-29
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.