Skip to main content
Glama
perplexity-mcp

perplexity-mcp

by madaoQ

Perplexity MCP Server

A Type 3 DAuth MCP server for Perplexity AI API. Provides web search, chat, embeddings, and content moderation using Perplexity's search-focused AI models.

Features

  • Search Answer — Real-time web search with citations

  • Chat — Conversational AI similar to chat completions

  • List Models — View available Perplexity models

  • Moderate — Content moderation

  • Embed — Text embeddings

Related MCP server: perplexity-mcp-server

Authentication

This server uses Type 3 DAuth (Dedalus Auth) — your API key is encrypted client-side and decrypted in a secure Dedalus enclave.

Get Your Perplexity API Key

  1. Go to https://www.perplexity.ai/settings/api

  2. Generate a new API key (requires paid subscription)

  3. Copy the key

Installation

git clone https://github.com/dedalus-labs/perplexity-mcp.git
cd perplexity-mcp
pip install -e .
cp .env.example .env
# Edit .env and add PERPLEXITY_API_KEY

Available Tools

perplexity_search_answer

Search the web and get answers with citations.

perplexity_search_answer(
    query="What is Model Context Protocol?",
    model="sonar",
    return_images=True,
    search_recency_days=7,
    temperature=0.2,
)

perplexity_chat

Chat with Perplexity AI.

perplexity_chat(
    model="sonar",
    messages=[{"role": "user", "content": "Hello!"}],
    temperature=0.2,
    max_tokens=500,
)

perplexity_list_models

List available Perplexity models.

perplexity_list_models()

perplexity_moderate

Check content for harmful material.

perplexity_moderate(text="This is a test message")

perplexity_embed

Generate text embeddings.

perplexity_embed(
    input="Hello world",
    model="embed",
)

Cost & Rate Limits

Perplexity uses pay-per-token pricing. Check https://perplexity.ai/pricing for details.

Model

Input

Output

Sonar

$0.005/1M

$0.005/1M

Sonar Pro

$0.01/1M

$0.03/1M

Sonar Reasoning

$0.005/1M

$0.005/1M

Rate Limits

  • Free tier: Limited requests per day

  • Pro tier: 500 requests/day

  • Enterprise: Custom limits

Safety Notes

  • Requires paid API — Perplexity API requires a paid subscription

  • Monitor costs — Set up usage alerts at perplexity.ai/dashboard

  • Don't commit keys — Always use environment variables

Deploy to Dedalus

  1. Push to GitHub (public repo)

  2. Go to https://www.dedaluslabs.ai/dashboard

  3. Add Server → Connect GitHub repo

  4. Set PERPLEXITY_API_KEY as Required Credential

  5. Deploy

License

MIT

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      B
      quality
      D
      maintenance
      An MCP server integrating Perplexity AI's API to offer advanced search capabilities with support for multiple models and result configuration.
      1
      1
      MIT
    • A
      license
      Not graded
      quality
      D
      maintenance
      An MCP server that enables AI agents to perform search-augmented queries and deep multi-source research using the Perplexity API.
      26
      Apache 2.0
    • A
      license
      C
      quality
      D
      maintenance
      MCP server providing 22 tools to query Perplexity AI's premium models (GPT-5.4, Claude 4.7 Opus, etc.) with citations, source discovery, and rate limit checking for AI agents.
      23
      21
      MIT