MCP Servers

Perplexity MCP Server (Python)

A Python port of the official Perplexity MCP server that enables web-grounded Q\&A, deep research, and step-by-step reasoning via Perplexity AI's models. It supports both STDIO and HTTP interfaces for seamless integration with tools like Claude Desktop and Cursor.

README

Perplexity MCP Server — Python Port

Python conversion of the official perplexityai/modelcontextprotocol Node.js/TypeScript server.

File mapping

TypeScript (original)	Python (this port)	Notes
`src/types.ts`	`types.py`	Dataclasses replace TS interfaces
`src/validation.ts`	`validation.py`	Pydantic models replace Zod schemas
`src/logger.ts`	`logger.py`	Direct translation
`src/server.ts`	`server.py`	Core MCP tools + API logic
`src/index.ts`	`__main__.py`	STDIO entry point
`src/http.ts`	`http_server.py`	HTTP entry point (FastAPI + uvicorn)

Dependencies

Node.js	Python
`@modelcontextprotocol/sdk`	`mcp`
`axios` / `undici` (fetch)	`httpx`
`zod`	`pydantic`
`express` + `cors`	`fastapi` + `CORSMiddleware`
Node.js built-ins	Python stdlib (`asyncio`, `re`, `json`, …)

Installation

pip install -e .

Usage

STDIO (for Claude Desktop, Cursor, VS Code…)

export PERPLEXITY_API_KEY=your_key_here
python -m perplexity_mcp
# or after pip install:
perplexity-mcp

Claude Desktop / Cursor mcpServers config:

{
  "mcpServers": {
    "perplexity": {
      "command": "perplexity-mcp",
      "env": { "PERPLEXITY_API_KEY": "your_key_here" }
    }
  }
}

HTTP server

export PERPLEXITY_API_KEY=your_key_here
python -m perplexity_mcp.http_server
# or after pip install:
perplexity-mcp-http

The server listens on http://0.0.0.0:8080/mcp by default.

Environment variables

Variable	Description	Default
`PERPLEXITY_API_KEY`	Perplexity API key (required)	—
`PERPLEXITY_BASE_URL`	Custom API base URL	`https://api.perplexity.ai`
`PERPLEXITY_TIMEOUT_MS`	Request timeout in ms	`300000`
`PERPLEXITY_PROXY`	Proxy URL	—
`HTTPS_PROXY` / `HTTP_PROXY`	Fallback proxy env vars	—
`PERPLEXITY_LOG_LEVEL`	`DEBUG\|INFO\|WARN\|ERROR`	`ERROR`
`PORT`	HTTP server port	`8080`
`BIND_ADDRESS`	HTTP bind address	`0.0.0.0`
`ALLOWED_ORIGINS`	CORS origins (comma-separated)	`*`

Available tools

Tool	Model	Description
`perplexity_ask`	`sonar-pro`	Quick Q&A with web grounding
`perplexity_research`	`sonar-deep-research`	Deep multi-source research (30s+)
`perplexity_reason`	`sonar-reasoning-pro`	Step-by-step reasoning + web
`perplexity_search`	Search API	Raw ranked URL results

Recommended Servers

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official

Featured

TypeScript

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official

Featured

Local

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official

Featured

TypeScript

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official

Featured

Python

E2B

Using MCP to run code via e2b.

Official

Featured

Neon Database

MCP server for interacting with Neon Management API and databases

Official

Featured

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official

Featured

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official

Featured