perplexityai/modelcontextprotocol

The official MCP server implementation for the Perplexity API Platform

What it solves

This project provides an official bridge between the Perplexity AI platform and AI-powered development environments. It allows developers to integrate Perplexity’s real-time web search, deep research, and reasoning capabilities directly into their IDEs (like Cursor or VS Code) or other AI agent workflows.

How it works

It implements the Model Context Protocol (MCP), a standard that allows AI applications to connect to external data and tools. By running this server, your AI assistant gains access to specific tools—such as web search or deep research—that it can trigger to fetch up-to-date information or perform complex analysis without leaving your editor.

Who it’s for

Developers and power users who want to augment their local AI coding assistants with Perplexity’s live search and research capabilities, or engineers building custom AI agents who need a standardized way to plug in Perplexity’s API.

Highlights

  • Direct Integration: Seamlessly adds Perplexity tools to popular editors like Cursor, VS Code, and Windsurf.
  • Versatile Toolset: Includes dedicated tools for general searching, deep research, and advanced reasoning.
  • Flexible Deployment: Can be used as a remote service, a local process, or embedded as a library in custom Node.js applications.
  • Enterprise-Ready: Supports proxy configurations for corporate network environments and provides options for self-hosted HTTP deployments.

Related

  • Project
    helallao/perplexity-ai

    Unofficial Perplexity AI client with account automation, MCP server, sync/async APIs, and browser-based account generation to bypass query limits.

  • Project
    DMontgomery40/deepseek-mcp-server

    DeepSeek MCP Server is a Node.js bridge that lets MCP‑compatible tools talk to DeepSeek’s V4.1 Flash and V4 Pro models. It supports chat (including image inputs), the Responses API, fill‑in‑the‑middle completions, model discovery, balance checks, and a full Files API for reusable images. Run it via stdio or as a local HTTP endpoint, providing only your DeepSeek API key.

  • Project
    anysearch-ai/anysearch-mcp-server

    AnySearch MCP Server is a real‑time, HTTP‑based MCP endpoint that lets LLM‑powered agents perform general web search, vertical‑domain search, parallel batch queries, and full‑page content extraction. It works with an optional API key (higher limits) or anonymously (lower limits) and provides ready‑made configuration snippets for all major AI‑coding assistants (OpenCode, Claude Code, Cursor, VS Code, Cline, Codex, Antigravity, DeepSeek Harness, Hermes Agent, OMP).

  • Project
    classfang/ssh-mcp-server

    ssh‑mcp‑server is a Node‑JS bridge that lets MCP‑compatible AI assistants run SSH commands, transfer files, and manage background jobs on remote servers. It keeps credentials local, offers whitelist/blacklist safety, supports password, key, and 2FA auth, works through proxies and bastion hosts, and can be run instantly with `npx`.

  • Project
    tavily-ai/tavily-mcp

    Tavily MCP is a Model Context Protocol server that exposes four web‑knowledge tools—search, extract, map, and crawl—so LLM‑based agents (Claude Code, Cursor, etc.) can fetch up‑to‑date web data, pull page content, generate site maps, or bulk‑crawl sites. It can be used via Tavily’s hosted endpoint or run locally with a single `npx` command, authenticating with an API key or optional OAuth. Configuration is done through environment variables (`TAVILY_API_KEY`, `DEFAULT_PARAMETERS`, `TAVILY_HUMAN_ID`). The server enables real‑time web access for AI assistants, RAG pipelines, and productivity tools without custom scraping code.