perplexity-web-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| PPLX_HIDE | No | Set to `0` to show the browser window. | 1 |
| PPLX_BROWSER | No | Playwright channel to use: `chrome`, `msedge`, `chrome-beta`, ... If you set PPLX_PROFILE or PPLX_BROWSER, set the same value when you run `login`. | chrome, then msedge |
| PPLX_PROFILE | No | Browser profile that stores your login. Default profile location: Linux: ~/.local/share/perplexity-mcp/profile; macOS: ~/Library/Application Support/perplexity-mcp/profile; Windows: %LOCALAPPDATA%\perplexity-mcp\profile. If you set PPLX_PROFILE or PPLX_BROWSER, set the same value when you run `login`. | |
| PPLX_IDLE_CLOSE | No | Seconds without queries before the browser closes. | 60 |
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
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| perplexity_searchA | Ask Perplexity (web search + answer with citations) using the user's Perplexity Pro subscription. Args: query: The question or search query. mode: "auto" (fast), "pro" (Pro Search, default), "reasoning", or "deep_research" (slow, thorough). model: Optional raw Perplexity model_preference override (e.g. "pplx_pro"). academic: Search academic sources instead of the general web. |
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 1 tool
There is only one tool, so there is no possibility of misselection between competing tools. The single tool's purpose (web search with Perplexity) is unambiguous, with its modality variants folded into a `mode` argument rather than separate tools.
A single, clearly readable snake_case name (`perplexity_search`) that namespaces the provider and the action. There is no second naming convention to conflict with it.
One tool is a thin surface for a server that exposes four distinct search modes plus model overrides and academic filtering. Consolidating is reasonable, but the result sits at the low end of what an agent would expect from a dedicated search server.
For a search-and-answer domain, a single entry point that returns a cited answer covers the core workflow. Minor gaps remain: no conversation/follow-up continuation, no citation or source retrieval, and no way to poll or resume the slow `deep_research` mode.