Perplexity Polza Mcp Server

Please install the `perplexity-polza-mcp-server` MCP server into my current AI client (that's you).

Required prerequisites (do these first if not already done):
- **Install uv** — Install the uv package manager/runner, which is used to launch the MCP server from PyPI via uvx. Run: `curl -LsSf https://astral.sh/uv/install.sh | sh` (https://docs.astral.sh/uv/)
- **Install Python 3.11+** — Python 3.11 or newer is required to run the server package.
- **Create a Polza.ai API key** — Generate a Polza.ai API key for authenticating requests to Perplexity models through Polza.ai. (https://polza.ai/dashboard/api-keys)

Canonical MCP server config (stdio transport):
- command: `uvx`
- args: ["perplexity-polza-mcp-server@latest"]
- required environment variables:
  - `POLZA_AI_API_KEY`: Polza.ai API key used to authenticate requests. (example: `<your-polza-ai-api-key>`)
- optional environment variables:
  - `POLZA_BASE_URL`: Base URL for the OpenAI-compatible chat completions API. Default is the Polza.ai API v1 endpoint. (example: `<your-polza-base-url>`)
  - `PERPLEXITY_MODEL`: Default model used for the perplexity_ask tool. (example: `<perplexity-model>`)
  - `PERPLEXITY_RESEARCH_MODEL`: Default model used for the perplexity_research tool. (example: `<perplexity-research-model>`)
  - `LOG_LEVEL`: Logging level for the server. (example: `<log-level>`)

Note: Preferred install path is PyPI via uvx. The README also documents a local development/source run path, but uvx is the simplest portable configuration.

Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.