perplexity-mcp and perplexity-mcp-server

perplexity-mcp
58
Established
perplexity-mcp-server
34
Emerging
Maintenance 6/25
Adoption 10/25
Maturity 25/25
Community 17/25
Maintenance 2/25
Adoption 6/25
Maturity 9/25
Community 17/25
Stars: 287
Forks: 35
Downloads:
Commits (30d): 0
Language: JavaScript
License: MIT
Stars: 21
Forks: 10
Downloads:
Commits (30d): 0
Language: TypeScript
License: Apache-2.0
No Dependents
Stale 6m No Package No Dependents

About perplexity-mcp

DaInfernalCoder/perplexity-mcp

A Model Context Protocol (MCP) server for research and documentation assistance using Perplexity AI. Won 1st @ Cline Hackathon

Implements automatic query complexity detection that routes between three Perplexity models—Sonar Pro for quick lookups, Sonar Reasoning Pro for multi-step analysis, and Sonar Deep Research for comprehensive reports—with optional manual override via `force_model` parameter. Exposes three MCP tools with integrated web search across all tasks, designed to enforce specificity from calling agents. Configurable via environment variables, command-line arguments, or `.env` files with fallback resolution priority.

About perplexity-mcp-server

cyanheads/perplexity-mcp-server

A Perplexity API MCP server that unlocks Perplexity's search-augmented AI capabilities for LLM agents. Features robust error handling, secure input validation, and transparent reasoning with the showThinking parameter.

Implements dual tools for Perplexity API integration—a `perplexity_search` tool for fast, filtered queries with recency and domain controls, and a `perplexity_deep_research` tool for exhaustive multi-source analysis with configurable reasoning effort. Built on the MCP SDK with TypeScript, it supports both stdio and HTTP transports, includes cost estimation utilities, and provides robust authentication (JWT/OAuth) and structured logging via Hono. Designed to integrate directly with MCP-compatible clients like Cline for LLM-driven research workflows.

Scores updated daily from GitHub, PyPI, and npm data. How scores work