Skip to main content
Glama
ppl-ai

Perplexity API Platform MCP Server

by ppl-ai

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
PORTNoHTTP server port (for HTTP server deployment)8080
HTTP_PROXYNoStandard HTTP proxy environment variable (alternative to PERPLEXITY_PROXY)
HTTPS_PROXYNoStandard HTTPS proxy environment variable (alternative to PERPLEXITY_PROXY)
BIND_ADDRESSNoNetwork interface to bind to (for HTTP server deployment)0.0.0.0
ALLOWED_ORIGINSNoCORS origins, comma-separated (for HTTP server deployment)*
PERPLEXITY_PROXYNoProxy URL for corporate networks (e.g., https://your-proxy-host:8080 or https://username:password@your-proxy-host:8080)
PERPLEXITY_API_KEYYesYour Perplexity API key from the API Portal
PERPLEXITY_LOG_LEVELNoLog level: DEBUG, INFO, WARN, or ERRORERROR
PERPLEXITY_TIMEOUT_MSNoTimeout in milliseconds (default: 5 minutes)300000

Capabilities

Features and capabilities supported by this server

CapabilityDetails
tools
{
  "listChanged": true
}

Tools

Functions exposed to the LLM to take actions

NameDescription
perplexity_ask

Engages in a conversation using the Sonar API. Accepts an array of messages (each with a role and content) and returns a chat completion response from the Perplexity model.

perplexity_research

Performs deep research using the Perplexity API. Accepts an array of messages (each with a role and content) and returns a comprehensive research response with citations.

perplexity_reason

Performs reasoning tasks using the Perplexity API. Accepts an array of messages (each with a role and content) and returns a well-reasoned response using the sonar-reasoning-pro model.

perplexity_search

Performs web search using the Perplexity Search API. Returns ranked search results with titles, URLs, snippets, and metadata. Perfect for finding up-to-date facts, news, or specific information.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/ppl-ai/modelcontextprotocol'

If you have feedback or need assistance with the MCP directory API, please join our Discord server