Perplexity MCP Server
# Perplexity MCP Server
[](https://smithery.ai/server/mcp-server-perplexity)
MCP Server for the Perplexity API.
> :warning: **Limitations:**
> - The Claude Desktop client may timeout if Perplexity processing takes too long
> - This issue might be resolved if Claude Desktop implements support for long running operations and progress reporting in the future
> - Implementation updates to handle these features will be made if they become available
<a href="https://glama.ai/mcp/servers/hchfq9bydq"><img width="380" height="200" src="https://glama.ai/mcp/servers/hchfq9bydq/badge" alt="Perplexity Server MCP server" /></a>
## Components
### Tools
- **ask_perplexity**: Request chat completion with citations from Perplexity
## Quickstart
### Install
#### Claude Desktop
- On macOS: `~/Library/Application\ Support/Claude/claude_desktop_config.json`
- On Windows: `%APPDATA%/Claude/claude_desktop_config.json`
```
"mcpServers": {
"Perplexity": {
"command": "uvx",
"args": [
"mcp-server-perplexity"
],
"env": {
"PERPLEXITY_API_KEY": "your-perplexity-api-key"
}
}
}
```
TDQS
Scored across 1 tool
With only one tool, there is no possibility of confusion or overlap between tools. The tool 'ask_perplexity' has a singular, well-defined purpose for internet research with source-backed information, making it completely distinct by default.
The single tool name 'ask_perplexity' follows a clear verb_noun pattern and is the only naming convention present. There are no other tools to compare it to, so consistency is inherently perfect.
A single tool for a server named 'Perplexity MCP Server' feels thin and limited in scope. While the tool is specialized for research, the server's purpose suggests it could benefit from additional tools (e.g., for query refinement, citation management, or batch processing) to provide a more complete research workflow.
The tool surface is severely incomplete for a research-oriented server. It only offers a single query function without supporting operations like saving results, managing search history, filtering citations, or handling different query types. This creates significant gaps that will limit agent capabilities in research scenarios.