perplexity-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| PERPLEXITY_MODEL | No | The Perplexity model to use (defaults to 'sonar') | sonar |
| PERPLEXITY_API_KEY | Yes | Your Perplexity AI API key |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| perplexity_search_webC | Search the web using Perplexity AI with recency filtering |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| perplexity_search_web | Search the web using Perplexity AI and filter results by recency |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 1 tool
There is only one tool, so no ambiguity exists. The agent will always select this tool for web search tasks.
The single tool name follows a clear verb_noun pattern (perplexity_search_web), which is consistent and intuitive.
Having only one tool is minimal but acceptable for a narrowly focused 'search' server; however, it feels thin and could benefit from additional related tools.
The server only provides web search with recency filtering, lacking features like search result extraction, multiple search modes, or context handling, which limits its usefulness for comprehensive tasks.