Perplexity MCP Zerver is a Model Context Protocol server implementation that provides AI-powered research capabilities by interacting with the Perplexity website without requiring an API key. It uses browser automation to access Perplexity's web search, chat features, and specialized research tools.
Performs a search query on Perplexity.ai with support for different response detail levels:
Retrieves documentation and examples for specific technologies or libraries, with optional focus on particular contexts.
Locates and evaluates APIs based on specified requirements and context.
Analyzes code snippets to identify deprecated features within specific technology contexts.
Extracts main article text content from URLs using browser automation and Mozilla's Readability. Handles GitHub repositories via gitingest.com and supports recursive link exploration.
Maintains ongoing conversations with Perplexity AI, storing chat history locally in a database file.
Clone the repository:
git clone https://github.com/wysh3/perplexity-mcp-zerver.git
cd perplexity-mcp-zerver
Install dependencies using pnpm:
pnpm install
Build the server:
pnpm run build
Important notes:
You need to add the server to your MCP configuration file, which varies depending on the application you're using:
Add this to your cline_mcp_settings.json
:
{
"mcpServers": {
"perplexity-server": {
"command": "node",
"args": [
"/full/path/to/your/perplexity-mcp-zerver/build/index.js"
],
"env": {},
"disabled": false,
"alwaysAllow": [],
"autoApprove": [],
"timeout": 300
}
}
}
Add this to your claude_desktop_config.json
:
{
"mcpServers": {
"perplexity-server": {
"command": "node",
"args": [
"/full/path/to/your/perplexity-mcp-zerver/build/index.js"
],
"env": {},
"disabled": false,
"alwaysAllow": []
}
}
}
Important: Replace /full/path/to/your/perplexity-mcp-zerver/build/index.js
with the absolute path to the built index.js
file on your system. For Windows, use double backslashes in paths, e.g., C:\\Users\\username\\Documents\\perplexity-mcp-zerver\\build\\index.js
.
Each tool has specific parameters and capabilities, so you can be more specific in your requests to get better results.
There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json
file so that it is available in all of your projects.
If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json
file.
To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".
When you click that button the ~/.cursor/mcp.json
file will be opened and you can add your server like this:
{
"mcpServers": {
"cursor-rules-mcp": {
"command": "npx",
"args": [
"-y",
"cursor-rules-mcp"
]
}
}
}
To add an MCP server to a project you can create a new .cursor/mcp.json
file or add it to the existing one. This will look exactly the same as the global MCP server example above.
Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.
The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.
You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.