- Home
- MCP servers
- Perplexity
Perplexity
- python
8
GitHub Stars
python
Language
6 months ago
First Indexed
2 months ago
Catalog Refreshed
Documentation & install
Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.
Installation
Add the following to your MCP client configuration file.
Configuration
View docs{
"mcpServers": {
"nachoal-perplexity-mcp": {
"command": "python",
"args": [
"server.py"
],
"env": {
"PERPLEXITY_API_KEY": "YOUR_API_KEY"
}
}
}
}You deploy this MCP server to enable Claude and other MCP-enabled AIs to search the web using Perplexity. It runs locally as a Python process and exposes a simple interface that returns rich search results with sources, citations, and time-filtered recency.
How to use
Start the server locally and connect your MCP client to it as the search capability provider. You can run searches by calling the server with a web search query and optional recency filters (day, week, month, year). The server returns a detailed summary of results, key facts, sources, and any conflicting information.
How to install
Prerequisites: you need Python installed on your system. The server is a Python application, so ensure you have Python 3.x and pip available.
- Prepare your environment and dependencies.
pip install -e .
Additional notes
Configuration is done via an environment variable named PERPLEXITY_API_KEY. You can set it in your shell or place it in a .env file at the project root.
To start the server locally, run the Python script that serves the MCP endpoint.
The server can be tested with a dedicated test script that exercises a sample query and recency filter.
Available tools
search_web
Search the web using the Perplexity API and return a comprehensive results summary with sources and citations.
web_search_prompt
Create a formatted prompt for prompting the AI to perform a web search with a specified recency window and to summarize findings with cited sources.