- Home
- MCP servers
- Perplexity
Perplexity
- python
92
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": {
"tanigami-mcp-server-perplexity": {
"command": "uvx",
"args": [
"mcp-server-perplexity"
],
"env": {
"PERPLEXITY_API_KEY": "YOUR_API_KEY"
}
}
}
}You bridge the Perplexity API to your MCP workflow, enabling chat completions with citations as part of your automated reasoning and querying tasks. This MCP server runs locally via a lightweight runtime and exposes Perplexity functionality as a standard MCP endpoint for client integrations.
How to use
You use an MCP client to connect to the Perplexity MCP Server and initiate chat sessions that return citations. The server runs as a local stdio process and is started by your MCP runtime. Provide your Perplexity API key through the configured environment variable, and then your client can request chat completions with referenced sources.
How to install
Prerequisites you need before starting:
- A compatible MCP runtime that can launch stdio servers (e.g., uvx-based runner).
Steps to install and run the Perplexity MCP Server exactly as configured:
{
"mcpServers": {
"Perplexity": {
"command": "uvx",
"args": [
"mcp-server-perplexity"
],
"env": {
"PERPLEXITY_API_KEY": "your-perplexity-api-key"
}
}
}
}
Additional内容
Notes and considerations for smooth operation include handling potential timeouts with long-running Perplexity processing. If your client or runtime supports long-running operations and progress reporting, enable those features for better reliability. Monitor for any updates to the MCP server to improve handling of extended tasks in the future.
Available tools
ask_perplexity
Request a chat completion with citations from Perplexity