perplexity-mcp
A Type 3 DAuth MCP server for Perplexity AI API that provides web search, chat, embeddings, and content moderation using Perplexity's search-focused AI models.
README
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
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
- Go to https://www.perplexity.ai/settings/api
- Generate a new API key (requires paid subscription)
- 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
- Push to GitHub (public repo)
- Go to https://www.dedaluslabs.ai/dashboard
- Add Server → Connect GitHub repo
- Set
PERPLEXITY_API_KEYas Required Credential - Deploy
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.