This Model Context Protocol (MCP) server enables LLMs like Claude to perform internet research using the Perplexity API. It provides real-time, up-to-date information with source citations.
An MCP (Model Context Protocol) server that provides access to Perplexity AI’s powerful search capabilities, including web search, academic research, financial data, and advanced filtering options.
The Perplexity MCP server offers four specialized search functions, each optimized for different use cases. All functions automatically return source URLs, allowing LLMs to fetch additional information if needed.
perplexity_search
General web search with real-time information. Best for current events, general knowledge, and quick facts.
perplexity_academic_search
Automatically filters to academic sources (arxiv.org, pubmed, journals). Best for research papers, scientific studies, and scholarly content.
perplexity_financial_search
Optimized for financial domains and recent data. Best for stock analysis, earnings reports, SEC filings, and market trends.
perplexity_filtered_search
Advanced search with multiple filtering options. Best when you need specific domain filtering, content types, or location-based results.
./run.sh
The server requires a Perplexity API key and supports various configuration options through environment variables:
PERPLEXITY_API_KEY
: Your Perplexity AI API keyPERPLEXITY_DEFAULT_MODEL
: Default model to use (default: “sonar”)
sonar
: Fast, cost-effective search for quick factssonar-pro
: Comprehensive search with better depth and coveragePERPLEXITY_MAX_TOKENS
: Maximum tokens in response (default: 1024)PERPLEXITY_TEMPERATURE
: Response randomness 0-2 (default: 0.2)PERPLEXITY_TOP_P
: Nucleus sampling parameter (default: 0.9)PERPLEXITY_TOP_K
: Top-k sampling parameter (default: 0)PERPLEXITY_TIMEOUT
: Request timeout duration (default: 30s)PERPLEXITY_RETURN_IMAGES
: Include images by default (default: false)PERPLEXITY_RETURN_RELATED
: Include related questions by default (default: false)Run the server in MCP mode (default):
export PERPLEXITY_API_KEY="your-api-key"
./perplexity
Run integration tests against the real Perplexity API:
export PERPLEXITY_API_KEY="your-api-key"
./perplexity -test
To use this server with an MCP client, add it to your client configuration:
{
"servers": {
"perplexity": {
"command": "path/to/perplexity",
"env": {
"PERPLEXITY_API_KEY": "your-api-key"
}
}
}
}
Perform a general web search.
Parameters:
query
(required): The search querymodel
: Choose ‘sonar’ for quick searches or ‘sonar-pro’ for comprehensive results (default: sonar)search_domain_filter
: Array of domains to includesearch_exclude_domains
: Array of domains to excludesearch_recency_filter
: Time filter (hour, day, week, month, year)return_images
: Include imagesreturn_related_questions
: Include related questionsmax_tokens
: Maximum response tokenstemperature
: Response randomness (0-2)date_range_start
: Start date (YYYY-MM-DD)date_range_end
: End date (YYYY-MM-DD)location
: Geo-specific search locationExample:
{
"query": "latest AI developments",
"model": "sonar-pro",
"search_recency_filter": "week",
"return_citations": true
}
Search academic papers and scholarly content.
Parameters:
query
(required): The academic search querysubject_area
: Academic subject (e.g., “Physics”, “Computer Science”)model
: Defaults to ‘sonar-pro’ for comprehensive academic resultssearch_domain_filter
: Array of academic domainssearch_recency_filter
: Time filtermax_tokens
: Maximum response tokenstemperature
: Response randomnessExample:
{
"query": "quantum computing applications",
"subject_area": "Physics",
"search_recency_filter": "year"
}
Search financial data and SEC filings.
Parameters:
query
(required): The financial search queryticker
: Stock ticker symbol (e.g., “AAPL”)company_name
: Company namereport_type
: Financial report type (e.g., “10-K”, “10-Q”, “8-K”)model
: Defaults to ‘sonar-pro’ for comprehensive financial datasearch_recency_filter
: Time filterdate_range_start
: Report start datedate_range_end
: Report end datemax_tokens
: Maximum response tokensExample:
{
"query": "quarterly earnings",
"ticker": "MSFT",
"report_type": "10-Q",
"search_recency_filter": "month"
}
Advanced search with comprehensive filtering.
Parameters:
query
(required): The search querymodel
: Choose based on needs (defaults to sonar-pro)search_domain_filter
: Array of domains to includesearch_exclude_domains
: Array of domains to excludesearch_recency_filter
: Time filtercontent_type
: Type of content (news, academic, blog, etc.)file_type
: File type filter (pdf, doc, html, etc.)language
: Language filtercountry
: Country for geo-specific searchdate_range_start
: Start datedate_range_end
: End datereturn_citations
: Include citationsreturn_images
: Include imagesreturn_related_questions
: Include related questionsmax_tokens
: Maximum response tokenstemperature
: Response randomnesscustom_filters
: Object with additional key-value filtersExample:
{
"query": "renewable energy innovations",
"content_type": "news",
"language": "English",
"country": "Germany",
"search_recency_filter": "month",
"custom_filters": {
"industry": "energy",
"technology": "solar"
}
}
All search functions return responses in the following format:
Example response structure:
[Main search results content...]
## Source URLs
1. https://example.com/article1
2. https://example.com/article2
3. https://example.com/article3
## Detailed Sources
1. **Article Title**
URL: https://example.com/article1
Snippet: Brief excerpt from the article...
## Related Questions
- What are the latest developments?
- How does this compare to...?
Run unit tests:
go test ./pkg/...
Run integration tests with real API:
go run cmd/main.go -test
perplexity/
├── cmd/
│ └── main.go # MCP server entry point
├── pkg/
│ ├── types/ # API types and constants
│ ├── perplexity/ # Perplexity client and search functions
│ └── config/ # Configuration management
├── test/
│ └── integration_test.go # Integration tests
└── README.md
The server handles various error conditions:
Errors are returned with descriptive messages to help diagnose issues.
MIT License - see LICENSE file for details.
Model Context Protocol server for file modifications and control
A VMware ESXi/vCenter management server based on MCP (Model Control Protocol), providing simple REST API interfaces for virtual machine management.
an mcp server for hefeng weather api
An MCP server that provides LLMs with the ability to use GitHub issues as tasks