What modes does MCP Perplexity Server support?
It supports Ask mode and Search mode, configured via the `MCP_MODE` environment variable (default: 'ask').
@lostmind008
基本信息
Model Context Protocol server implementation for Perplexity API
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"perplexity-ask": {
"command": "npx",
"args": [
"-y",
"github:lostmind008/mcp-perplexity-server"
],
"env": {
"PERPLEXITY_API_KEY": "your-api-key",
"MCP_SERVER_PORT": "3000",
"MCP_MODE": "ask"
}
},
"perplexity-search": {
"command": "npx",
"args": [
"-y",
"github:lostmind008/mcp-perplexity-server"
],
"env": {
"PERPLEXITY_API_KEY": "your-api-key",
"MCP_SERVER_PORT": "3001",
"MCP_MODE": "search"
}
}
}
}工具列表暂未提供
当前收录暂时没有可展示的工具列表,不代表服务没有工具。请查阅项目文档了解支持的能力。
点击上方按钮,在临时沙箱中运行此服务器并实时获取工具列表。
An MCP server implementation that wraps the Perplexity API, supporting Ask and Search modes, designed for use with any MCP client.
Install by adding a configuration entry to your MCP client, specifying the command npx -y github:lostmind008/mcp-perplexity-server, and set the required environment variable PERPLEXITY_API_KEY plus optional MCP_SERVER_PORT and MCP_MODE. Invoke via the client using server names like perplexity-ask or perplexity-search.
It supports Ask mode and Search mode, configured via the `MCP_MODE` environment variable (default: 'ask').
Only `PERPLEXITY_API_KEY` is required. Optional variables: `MCP_SERVER_PORT` (default 3000) and `MCP_MODE` (default 'ask').
It runs automatically when invoked by an MCP client using `npx -y github:lostmind008/mcp-perplexity-server`. No local installation is needed.
The default port is 3000, but can be changed via `MCP_SERVER_PORT`.
It requires an MCP client to invoke it and a valid Perplexity API key. It runs via npx, so Node.js and npm must be available.

Hire a verified local human for small real-world tasks your AI agent can't do: errands, queues, pickups, in-person checks and on-site photos. Your agent posts a quest, local humans send offers, and your user picks one an

scvd.store is an evidence observatory for agentic commerce. Independent signed observation of what other people's endpoints, artifacts and payments actually did among other things. USDC on Base, Arbitrum One, World Chain
HeyLead: AI agent for LinkedIn outreach. Finds the right people, writes in your voice, follows up and handles replies, from Claude Code, Cursor, any MCP client or a web dashboard.

Docs: https://botchelor.com/agents and https://botchelor.com/llms.txt . Botchelor is a blind-date show for fictional characters, and AI agents are welcome to play. Over MCP, your agent builds an original character in w
Open-source Node.js FHIR MCP server with SMART Backend Services, metadata-aware search/CRUD tools, compact responses, FHIRPath filtering, safe pagination, audit events, and terminology lookup.
评论