perplexity-web-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| TIMEOUT | No | Optional. Maximum seconds to wait for an answer. Configure via the --timeout=N CLI flag (e.g., --timeout=30). | 20 |
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 | {} |
| logging | {} |
| completions | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| searchA | Search the web using Perplexity.ai and get an AI-synthesized answer with cited sources. Uses default Perplexity settings. |
| search_advancedA | Search Perplexity.ai with specific source selection. Lets you combine multiple sources (e.g. web + academic). Use this when source control matters; prefer |
| loginA | Check if you are authenticated on Perplexity.ai. If not, opens a browser window so you can log in. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 3 tools
Each tool has a clearly distinct purpose: search is for general queries, search_advanced provides explicit source control, and login handles authentication. There is no ambiguity between them.
search and search_advanced follow a consistent lowercase snake_case pattern, though login deviates from the 'search' prefix. The naming is still clear and predictable overall.
With only 3 tools, the set is minimal yet complete for its purpose—performing web searches and handling authentication. Each tool earns its place without bloat or redundancy.
The surface covers the full search lifecycle: a standard search, an advanced search with source selection, and an auth check to ensure access. No significant gaps are apparent for a web search MCP.