Perplexity MCP Server
@MCP-Mirror
About Perplexity MCP Server
Mirror of
Config
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"Perplexity": {
"command": "uvx",
"args": [
"mcp-server-perplexity"
],
"env": {
"PERPLEXITY_API_KEY": ""
}
}
}
}Tools
1Request chat completion with citations from Perplexity
Overview
What is Perplexity MCP Server?
Perplexity MCP Server is a Model Context Protocol server that provides a tool—ask_perplexity—for requesting chat completions with citations from the Perplexity API. It is designed for developers using MCP clients (such as Claude Desktop) who want to integrate Perplexity’s search-grounded answers.
How to use Perplexity MCP Server?
Install it by adding an entry to your Claude Desktop configuration file with the command uvx, arguments ["mcp-server-perplexity"], and the environment variable PERPLEXITY_API_KEY set to your Perplexity API key. Once configured, you can invoke the ask_perplexity tool from your MCP client to get chat completions with citations.
Key features of Perplexity MCP Server
- Exposes a single MCP tool:
ask_perplexity - Returns chat completions with citations from Perplexity
- Easy to install via
uvxand Claude Desktop config - Works with any MCP client supporting tools
Use cases of Perplexity MCP Server
- Query Perplexity for answers that include cited sources
- Incorporate factual, citation-backed responses into AI workflows
- Use Perplexity’s chat completion within MCP-enabled applications
FAQ from Perplexity MCP Server
What does the ask_perplexity tool do?
It requests a chat completion from Perplexity and returns the response along with citations.
What are the known limitations of this server?
The Claude Desktop client may timeout if Perplexity’s processing takes too long. This might be resolved if Claude Desktop adds support for long-running operations and progress reporting.
How do I configure the server?
Set the PERPLEXITY_API_KEY environment variable in your Claude Desktop configuration, using uvx as the command and mcp-server-perplexity as the argument.
Do I need an API key to use this server?
Yes, a valid Perplexity API key is required and must be provided via the PERPLEXITY_API_KEY environment variable.
Frequently asked questions
What does the `ask_perplexity` tool do?
It requests a chat completion from Perplexity and returns the response along with citations.
What are the known limitations of this server?
The Claude Desktop client may timeout if Perplexity’s processing takes too long. This might be resolved if Claude Desktop adds support for long-running operations and progress reporting.
How do I configure the server?
Set the `PERPLEXITY_API_KEY` environment variable in your Claude Desktop configuration, using `uvx` as the command and `mcp-server-perplexity` as the argument.
Do I need an API key to use this server?
Yes, a valid Perplexity API key is required and must be provided via the `PERPLEXITY_API_KEY` environment variable.
Basic information
More AI & Agents MCP servers
Solon Ai
opensolonJava AI application development framework (supports LLM-tool,skill; RAG; MCP; Agent-ReAct,Team-Agent). Compatible with java8 ~ java25. It can also be embedded in SpringBoot, jFinal, Vert.x, Quarkus, and other frameworks.

bsv.cx
Andy RoweTimestamp and verify evidence on-chain. Let your agent prove what it saw and when. bsv.cx gives an AI agent verifiable memory. Timestamp a hash of any output, archive a web page as it looked, or fetch a URL with a recei
MCP-LLM Bridge
patruffBridge between Ollama and MCP servers, enabling local LLMs to use Model Context Protocol tools
Just Prompt - A lightweight MCP server for LLM providers
dislerjust-prompt is an MCP server that provides a unified interface to top LLM providers (OpenAI, Anthropic, Google Gemini, Groq, DeepSeek, and Ollama)

Competitor Tracker & Co.
Competitor Tracker & Co.Competitor Tracker & Co. watches your competitors' websites and tells you what changed. Every week it crawls their pricing, product, messaging and corporate pages, detects the changes that matter, and files a tagged, ran
Comments