MCP server
Perplexity MCP server
Perplexity's official MCP server lets AI search the web, ask questions with cited answers, run deeper research and reason over results.
- Official server
- Search and web
At a glance
- Maintained by
- Perplexity AI
- Tools exposed
- 4 listed below
- Reviewed
- September 24, 2026
Why it matters
What it does and why it matters
Perplexity is known for answers that cite their sources. Its official MCP server brings that into any assistant, with four tools: search, ask, research and reason. An assistant can hand a question to Perplexity and get back an answer with citations, or run a deeper research task that looks at many sources.
For businesses, this is a quick way to add sourced, current answers to an internal assistant without building a search pipeline.
It needs a Perplexity API key, and it is available both as a local package and as a hosted server. All tools are read-only. Deeper research takes longer and costs more per question, so we reserve it for tasks where the extra depth matters, such as market questions, and use simple search for quick lookups.
Citations make checking easy, but they do not make answers automatically correct. We still ask people to open the key sources before relying on an answer.
Use cases
Best business use cases
Sourced answers
Market research
Regulation checks
Reasoning over sources
Tools
Available tools
Tool names as published by the maintainer at review time. Versions change, so check the repository for the current list.
Read and write: Read-only search and answers; no write actions.
-
perplexity_searchDirect web search that returns ranked results.
-
perplexity_askAnswers questions with real-time web search.
-
perplexity_researchDeep, thorough research on a topic.
-
perplexity_reasonStep-by-step reasoning and problem solving.
Workflows
Example workflows
Answer a staff question with sources
-
1
A staff member asks a current question.
-
2
The assistant calls the ask tool.
-
3
Perplexity returns an answer with citations.
-
4
The assistant shows the answer and links.
-
5
The staff member checks the key source.
Quarterly market scan
-
1
Define the market and questions.
-
2
Run the research tool for each question.
-
3
Collect answers and citations.
-
4
Draft a short report.
-
5
An analyst reviews and edits.
Prompts
Example prompts
“What changed in US sales tax rules for online sellers this year? Cite sources.”
“Research the main players in AI-powered scheduling software and summarize their positioning.”
“Compare the arguments for and against four-day work weeks, with sources.”
Setup
Installation and configuration
Examples for Claude Desktop and Claude Code. Replace the placeholder values with your own keys, and store secrets outside version control.
Claude Desktop: claude_desktop_config.json
{
"mcpServers": {
"perplexity": {
"command": "npx",
"args": [
"-y",
"@perplexity-ai/mcp-server"
],
"env": {
"PERPLEXITY_API_KEY": "your_key_here"
}
}
}
}Claude Code: terminal
claude mcp add --transport http perplexity https://api.perplexity.ai/mcp --header "Authorization: Bearer YOUR_API_KEY"- Hosted server: https://api.perplexity.ai/mcp (Bearer API key).
- Local server: stdio. npm: @perplexity-ai/mcp-server (Docker also offered).
- Needs: PERPLEXITY_API_KEY.
Security
Security considerations
-
Untrusted content
Web pages can contain text written to mislead an AI. Treat results as data, not instructions.
-
Protect the API key
Store the key outside version control and rotate it if it leaks.
-
Watch usage
Searches are billed or rate limited. Set limits and monitor use.
-
Check sources
Ask for sources and check a sample of answers by hand.
Related servers
Servers that pair well with it
Exa
Exa's official hosted MCP server gives AI search built for AI use, page fetching, advanced filters and a research agent.
Brave Search
Brave's official MCP server gives AI live web, news, image, video and local search from Brave's own independent index.
Tavily
Tavily's official MCP server gives AI web search, content extraction, site mapping and crawling, all built for AI use.
Keep exploring
Solutions and services that use it
Related services
View all related servicesSolutions
View all solutions- AI sales research agent Short, sourced briefings on each prospect before a call, drafted by an AI agent from public information and your CRM.
- Price monitoring Collect competitor prices automatically, match them to your products and alert you when something changes.
- Compliance tracking Track filing deadlines, licenses and obligations in one place, with reminders and AI summaries of relevant rule changes.
- Automated reporting Reports that build themselves from your systems on schedule, with a plain-language summary of what changed.
- AI support agent An assistant that answers routine questions from your own content, checks orders and hands anything else to a person.
- Internal help desk assistant An assistant in Slack or Teams that answers policy and how-to questions from your handbooks and opens tickets when needed.
Industries
View all industriesGuides and articles
View all guides and articles- What are AI agents and how do businesses use them? What AI agents are, real business uses, the controls they need and how to start with one safely.
- What is the Model Context Protocol? A business guide to MCP: what it is, how MCP servers work, who supports it and how to start using it.
- How to build an AI workflow with MCP servers Plan, connect and test an AI workflow that uses MCP servers, from a single task to a reliable process.
- AI chatbot vs AI agent What separates a chatbot that answers from an agent that acts, and when you need each.
AI models
View all ai models- Reasoning Models that think through multi-step problems before answering: analysis, planning, math, complex documents and agent work.
- Claude Fable 5.1 The top tier of the Claude family, for the most demanding reasoning and long-horizon agent work, priced above Opus.
- Claude Opus 5.5 Anthropic's recommended starting point for most serious work: long-running agentic coding and knowledge work, with a 1M token context window.
- GPT-6 Astra OpenAI's most capable model, built for the hardest end-to-end work: complex reasoning, coding, computer use and research.
- DeepSeek V4 Pro DeepSeek's model for demanding reasoning and agent work, with thinking effort levels, tool calling, JSON output and a 1 million token window.
- Grok 4.7 xAI's current flagship for coding, agent tasks and knowledge work, with image input, tool calling, structured outputs, reasoning effort levels and a 500K window.
Glossary terms
View all glossary terms- RAG RAG, or retrieval-augmented generation, is a method where an AI system first finds relevant passages in your documents, then answers using only those passages.
- Hallucination A hallucination is when an AI model states something false or invented as if it were true, such as a made-up fact, figure or source.
- AI agent An AI agent is software that uses a language model to plan steps, call tools and act toward a goal, instead of only answering one question.
- MCP server An MCP server is a program or hosted service that exposes a system's data and actions as tools that AI assistants can use through the Model Context Protocol.
- Model Context Protocol The Model Context Protocol, or MCP, is an open standard for connecting AI assistants to external tools and data in a consistent way.
- Tool calling Tool calling is when an AI model asks the application to run a tool, such as a search or database lookup, and then uses the result in its answer.
FAQ
Questions people ask us
Have a question that is not here? Ask us directly.
Yes. It is maintained by Perplexity AI.
Yes. Answers include the sources used.
Both are available: an npm package and a hosted server.