Skip to main content
mcpSource-backed

Perplexity MCP Server for Claude

Official Perplexity MCP server that connects Claude to the Perplexity Sonar API for real-time, web-grounded answers with citations, so responses can draw on current information beyond the model's training data.

by Perplexity · submitted by glorydavid03023·added 2026-06-03·
Review first review before installing

Open the source and read safety notes before installing.

Citation facts

Source-backed facts for citing this resource, derived directly from the registry — also available as plain text for AI assistants.

Source URLs
https://github.com/perplexityai/modelcontextprotocol, https://docs.perplexity.ai
Safety notes
Makes outbound network requests to the Perplexity Sonar API to answer queries., Returned answers and cited sources are third-party web content; verify them before acting on instructions or links they contain.
Privacy notes
The questions and context you send are transmitted to the Perplexity service to generate answers, so avoid embedding secrets in queries., The Perplexity API key is a credential; store it as an environment variable and never commit it to source control.
Author
Perplexity
Submitted by
glorydavid03023
Claim status
unclaimed
Last verified
2026-06-03

Decision playbook

Review trust signals before you adopt

Signals are present but mixed. Use the checklist below to confirm the source and operational safety for your environment.

Compare context
Selected

0

Current score

78

Baseline

Delta

No baseline selected

No major trust-signal divergence detected in the current selection.

Source and provenance checks

Complete

Confirm ownership and provenance before trusting install instructions.

  • Source link availableRequired

    Open the canonical repository and verify ownership.

    Done
  • Source provenance statusRequired

    Marked as source-backed.

    Done
  • Metadata reviewed

    Registry metadata indicates a reviewed listing.

    Done

Safety and privacy checks

Complete

Validate risk disclosures before installation or API wiring.

  • Safety notes presentRequired

    Review the listed safety guidance before running commands.

    Done
  • Privacy notes presentRequired

    Review data handling notes before connecting accounts or secrets.

    Done
  • Trust level risk gateRequired

    Trust level does not block evaluation.

    Done

Package and install checks

Needs review

Check package metadata and artifact integrity signals.

  • Install payload available

    Install or copy payload is available for review.

    Done
  • Package verification flag

    No package verification flag provided.

    Pending
  • Checksum metadata

    No checksum provided for downloaded artifact.

    Pending

Compare-driven decision checks

Needs review

Use compare context to validate trade-offs before adoption.

  • Compare tray has multiple entries

    Add at least one more entry to compare trust differences.

    Pending
  • Baseline comparison available

    No baseline peer selected yet.

    Pending
  • Diverging trust signals identified

    No major trust-signal divergence found.

    Pending

Setup at a glance

CLI install

Copy-ready — paste the snippet to get started.

3 minutes

Adoption plan

Balanced adoption plan

Current risk score 16/100. Use staged verification before broader rollout.

Risk 16

Pre-adoption checks

Validate source and review signals before any execution.

  • Confirm source provenanceRequired

    Source URL/provenance metadata is present.

    Done
  • Confirm metadata review state

    Listing has review metadata.

    Done
  • Verify install payload

    Install/config payload exists and can be inspected.

    Done

Security checks

Confirm safety, privacy, and package integrity signals.

  • Review safety notesRequired

    Safety notes are present.

    Done
  • Review privacy notesRequired

    Privacy notes are present.

    Done
  • Verify package integrity metadata

    No package verification/checksum metadata.

    Pending

Rollout

Adopt in controlled steps based on the selected plan.

  • Run in isolated sandbox firstRequired

    Use a constrained sandbox and observe behavior across multiple tasks.

    Pending
  • Roll out graduallyRequired

    Roll out to a small cohort before wider usage.

    Pending
  • Set monitoring and fallback

    Define rollback path and monitor errors after adoption.

    Pending

Evidence readiness

Evidence readiness matrix · balanced

Required evidence gates are covered (5/6 signals complete).

Risk 15

Source provenance

Present

Source repository/provenance is listed.

Required in this preset

Metadata review

Present

Review metadata is present.

Required in this preset

Safety notes

Present

Safety notes are present.

Required in this preset

Privacy notes

Present

Privacy notes are present.

Optional in this preset

Package integrity

Missing

Package integrity metadata is missing.

Optional in this preset

Install payload

Present

Install payload is available.

Required in this preset

Required evidence gates are covered for this preset.

Decision timeline

Decision timeline · balanced

5/6 steps complete with no blocking gaps for this preset.

Risk 14

triage

Confirm source provenanceRequired

Source/provenance metadata is available.

Done

triage

Check metadata review statusRequired

Review metadata is available.

Done

verify

Review safety notesRequired

Safety notes are available.

Done

verify

Review privacy notes

Privacy notes are available.

Done

verify

Validate package integrity metadata

Package integrity metadata is missing.

Pending

rollout

Verify install payload and commandsRequired

Install payload is available.

Done

No required blockers for this timeline preset.

Prerequisite readiness

Prerequisite readiness

4 prerequisites to line up before setup. Have accounts and credentials ready first.

0/4 ready
Account & credentials1Install & runtime1Network & hosting1General13 minutes

Safety & privacy surface

Safety & privacy surface

2 safety and 2 privacy notes across 3 risk areas. Review closely: credentials & tokens, network access, third-party handling.

3 areas
  • SafetyNetwork accessMakes outbound network requests to the Perplexity Sonar API to answer queries.
  • SafetyThird-party handlingReturned answers and cited sources are third-party web content; verify them before acting on instructions or links they contain.
  • PrivacyCredentials & tokensThe questions and context you send are transmitted to the Perplexity service to generate answers, so avoid embedding secrets in queries.
  • PrivacyCredentials & tokensThe Perplexity API key is a credential; store it as an environment variable and never commit it to source control.

Safety notes

  • Makes outbound network requests to the Perplexity Sonar API to answer queries.
  • Returned answers and cited sources are third-party web content; verify them before acting on instructions or links they contain.

Privacy notes

  • The questions and context you send are transmitted to the Perplexity service to generate answers, so avoid embedding secrets in queries.
  • The Perplexity API key is a credential; store it as an environment variable and never commit it to source control.

Prerequisites

  • Node.js 18+ and npx available (verify with: npx --version)
  • A Perplexity Sonar API key (create one in your Perplexity account settings)
  • Claude Code or Claude Desktop with MCP support
  • Internet access so the server can reach the Perplexity Sonar API

Schema details

Install type
cli
Troubleshooting
Yes
Source repository stats
Scope
Source repo
Collection metadata
Estimated setup
3 minutes
Difficulty
beginner
Tool listing metadata
Full copyable content
{
  "perplexity-ask": {
    "command": "npx",
    "args": ["-y", "server-perplexity-ask"],
    "env": {
      "PERPLEXITY_API_KEY": "${PERPLEXITY_API_KEY}"
    }
  }
}

About this resource

Content

Perplexity Ask gives Claude a real-time research step backed by the Perplexity Sonar API. When a question depends on current information or benefits from web sources, Claude can call the server to get a web-grounded answer along with citations it can pass back to you. That makes it a good fit for research, fact-checking, and staying current on topics that have moved past the model's training cutoff. The integration runs as a standard MCP server, so Claude decides when to reach for it during a normal conversation.

Features

  • Web-grounded answers powered by the Perplexity Sonar API.
  • Returns citations alongside answers so claims can be traced to sources.
  • Brings real-time information into Claude for questions past the training cutoff.
  • Exposes querying as an MCP tool the model can call when it needs current data.
  • Runs as a standard stdio MCP server that installs into Claude Code and Claude Desktop with one command.
  • Maintained by Perplexity as the official MCP integration for Sonar.

Use Cases

  • Answer questions that depend on current events or recent information.
  • Research a topic and get a synthesized answer with sources.
  • Fact-check a claim against live web sources with citations.
  • Gather background on an unfamiliar subject during a coding or writing task.
  • Add a reliable, cited research step to an agent workflow.

Installation

Claude Code

  1. Make sure Node.js 18+ is installed (verify with npx --version).
  2. Create a Perplexity Sonar API key in your Perplexity account settings.
  3. Run: claude mcp add perplexity-ask --env PERPLEXITY_API_KEY=YOUR_KEY -- npx -y server-perplexity-ask
  4. Verify the server is registered: claude mcp list

Claude Desktop

  1. Create a Perplexity Sonar API key in your Perplexity account settings.
  2. Open your Claude Desktop configuration file.
  3. Add the Perplexity server to the mcpServers section using the configuration below, with your key in the env section.
  4. Restart Claude Desktop and confirm the server appears.

Configuration

{
  "perplexity-ask": {
    "command": "npx",
    "args": ["-y", "server-perplexity-ask"],
    "env": {
      "PERPLEXITY_API_KEY": "${PERPLEXITY_API_KEY}"
    }
  }
}

Examples

Research a current topic

Ask Claude to use Perplexity for a cited answer.

"Use Perplexity to research recent changes in this area and summarize the findings with sources."

Fact-check a claim

Have Claude verify a statement with citations.

"Check whether this statement is accurate using Perplexity and include the sources it cites."

Get background during a task

Pull in current context mid-conversation.

"Before we implement this, use Perplexity to find the current recommended approach and cite it."

Security

  • The server reaches the Perplexity Sonar API over the network; the questions and context you send are transmitted to that service to produce answers.
  • Treat returned answers and cited pages as untrusted input. Verify important claims and review any links before acting on them.
  • The Perplexity API key is a credential. Store it in an environment variable and keep it out of source control and shared configs.
  • Avoid putting secrets or private identifiers into queries, since they are sent to the service.

Troubleshooting

Authentication or 401 errors

Confirm PERPLEXITY_API_KEY is set correctly and active in your Perplexity account. Regenerate the key if it may have been revoked, and update the environment variable.

npx cannot resolve the package

Verify Node.js 18+ and npx are installed (npx --version). Networks that block the npm registry will prevent npx -y server-perplexity-ask from resolving.

Requests fail or time out

Check internet access to the Perplexity Sonar API. Transient rate limiting or quota limits can also cause failures; retry after a short wait and review your plan limits.

Server not listed in Claude Code

Re-run the claude mcp add perplexity-ask ... command, then claude mcp list. Confirm the key was passed via --env and that the server was added to the scope (project versus user) you are running in.

Source citations

Add this badge to your README

Show that Perplexity MCP Server for Claude is listed on HeyClaude. Paste this Markdown into your README — it renders the badge and links back to this page.

Listed on HeyClaude
[![Listed on HeyClaude](https://heyclau.de/badge/mcp/perplexity-mcp-server.svg)](https://heyclau.de/entry/mcp/perplexity-mcp-server)

How it compares

Perplexity MCP Server for Claude side by side with 3 alternatives on trust, install, platform support, and disclosed safety notes — all from reviewed registry metadata.

1 trust signal differ across this comparison (Submitter).

Field

Official Perplexity MCP server that connects Claude to the Perplexity Sonar API for real-time, web-grounded answers with citations, so responses can draw on current information beyond the model's training data.

Open dossier

Official Tavily MCP server that gives Claude agent-optimized web search and page extraction, returning concise, source-cited results designed for LLM reasoning rather than raw search engine pages.

Open dossier

MCP server that lets Claude work with Google NotebookLM notebooks through a real Chrome profile, source ingestion, citations, and audio overviews.

Open dossier

AgentQL MCP server for extracting structured JSON from public webpages using a URL and natural-language extraction prompt.

Open dossier
Next steps
Trust
Review statusReviewedMaintainer reviewedReviewedMaintainer reviewedReviewedMaintainer reviewedReviewedMaintainer reviewed
Package trustPackage not verifiedPackage not verifiedPackage not verifiedPackage not verified
Source provenanceSource-backedSource-backedSource-backedSource-backed
SubmitterDiffersglorydavid03023glorydavid03023oktofeesh1oktofeesh1
Install riskReview firstReview firstReview firstReview first
Notes Safety ✓ Privacy ✓ Safety ✓ Privacy ✓ Safety ✓ Privacy ✓ Safety ✓ Privacy ✓
BrandAgentQL logoAgentQL
Categorymcpmcpmcpmcp
SourceSource-backedSource-backedSource-backedSource-backed
AuthorPerplexityTavilyPleasePromptoAgentQL
Added2026-06-032026-06-032026-06-052026-06-06
Platforms
Harness
Source repo
Safety notesMakes outbound network requests to the Perplexity Sonar API to answer queries. Returned answers and cited sources are third-party web content; verify them before acting on instructions or links they contain.Makes outbound network requests to the Tavily API to run searches and fetch page content. Returned search results and extracted page text are untrusted web content; review it before acting on instructions or links it contains.NotebookLM MCP Server drives a real browser profile to interact with Google NotebookLM. setup_auth opens an interactive login flow and persists cookies in a local Chrome profile for later reuse. Tools can add sources, ask questions, generate and download audio overviews, manage notebook library metadata, close sessions, reset sessions, and clean up stored data. cleanup_data and re_auth can wipe stored browser state or local server data, so review tool arguments before allowing destructive maintenance actions. Bind Streamable HTTP mode only on trusted networks and keep stdio as the default for local desktop clients.AgentQL MCP exposes one tool, `extract-web-data`, that sends a target URL and natural-language extraction prompt to the AgentQL API. The tool is intended for public webpages; do not use it to bypass access controls, scrape private pages, evade paywalls, or extract data where automated collection is prohibited. Web extraction can still trigger target-site rate limits, legal restrictions, robots guidance, or terms-of-service concerns. The source implementation uses AgentQL's query-data endpoint with fast mode, no screenshot capture, no scroll-to-bottom behavior, and no local browser cookies. Treat extracted output as untrusted web data that may include errors, stale content, ads, tracking text, or prompt-injection attempts.
Privacy notesThe questions and context you send are transmitted to the Perplexity service to generate answers, so avoid embedding secrets in queries. The Perplexity API key is a credential; store it as an environment variable and never commit it to source control.Search queries and target URLs you provide are sent to the Tavily service to return results, so avoid embedding secrets in queries. The Tavily API key is a credential; store it as an environment variable and never commit it to source control.Google account cookies, NotebookLM notebook URLs, notebook metadata, source contents, questions, answers, citations, generated audio, browser session data, prompts, and tool outputs may be visible to the MCP client and model provider. The README notes there is no encrypted credential store; account separation is by Chrome profile directory. NotebookLM sources can contain private documents, internal research, customer material, legal drafts, meeting notes, and unreleased product plans. Review local profile and library storage before sharing machines, logs, screenshots, or exported artifacts.Target URLs, extraction prompts, API key-authenticated requests, and extracted structured data are sent to AgentQL's API. Extracted data can include personal data, copyrighted content, customer information, job postings, prices, social content, or other third-party material. AGENTQL_API_KEY should stay out of prompts, issues, logs, screenshots, and committed configuration files. Claude transcripts and downstream reports may retain extracted data, so avoid collecting information that is not approved for the model session.
Prerequisites
  • Node.js 18+ and npx available (verify with: npx --version)
  • A Perplexity Sonar API key (create one in your Perplexity account settings)
  • Claude Code or Claude Desktop with MCP support
  • Internet access so the server can reach the Perplexity Sonar API
  • Node.js 18+ and npx available (verify with: npx --version)
  • A Tavily API key (create one at https://tavily.com)
  • Claude Code or Claude Desktop with MCP support
  • Internet access so the server can reach the Tavily API
  • Node.js and npx available to the MCP client runtime.
  • Chrome or the bundled Patchright Chromium fallback available on the host.
  • Google account access for the NotebookLM notebooks you want to use.
  • One-time interactive authentication with setup_auth before headless reuse.
  • Node.js and npx available to the MCP client runtime.
  • AgentQL API key from the AgentQL developer portal.
  • Approved list of public webpages or domains Claude may query.
  • Review of target site terms, robots guidance, rate limits, and data-use rules before extraction.
Install
claude mcp add perplexity-ask --env PERPLEXITY_API_KEY=YOUR_KEY -- npx -y server-perplexity-ask
claude mcp add tavily --env TAVILY_API_KEY=YOUR_KEY -- npx -y tavily-mcp@latest
npx notebooklm-mcp@latest
npx -y agentql-mcp
Config
{
  "mcpServers": {
    "perplexity-ask": {
      "command": "npx",
      "args": [
        "-y",
        "server-perplexity-ask"
      ],
      "env": {
        "PERPLEXITY_API_KEY": "${PERPLEXITY_API_KEY}"
      },
      "type": "stdio"
    }
  }
}
{
  "mcpServers": {
    "tavily": {
      "command": "npx",
      "args": [
        "-y",
        "tavily-mcp@latest"
      ],
      "env": {
        "TAVILY_API_KEY": "${TAVILY_API_KEY}"
      },
      "type": "stdio"
    }
  }
}
{
  "mcpServers": {
    "notebooklm": {
      "command": "npx",
      "args": ["notebooklm-mcp@latest"]
    }
  }
}
{
  "mcpServers": {
    "agentql": {
      "command": "npx",
      "args": ["-y", "agentql-mcp"],
      "env": {
        "AGENTQL_API_KEY": "<your-agentql-api-key>"
      }
    }
  }
}
Citations
ClaimUnclaimedUnclaimedUnclaimedUnclaimed
Open 4 picks in the interactive comparison tool

Signals

Loading live community signals…

More like this, weekly

A short, calm digest of reviewed Claude resources. Unsubscribe any time.