Praisonai

Please install the `praisonai` MCP server into my current AI client (that's you).

Required prerequisites (do these first if not already done):
- **Obtain OpenAI API key** — Required for agent tools and practical default operation of the server. (https://platform.openai.com/api-keys)

Optional prerequisites:
- Install uv — Install uv to run the recommended `uvx` command for the MCP server. Run: `pip install uv` (https://docs.astral.sh/uv/)
- Optional search provider API keys — Obtain API keys for Tavily, Exa, or You.com if you want to use their corresponding search tools.

Canonical MCP server config (stdio transport):
- command: `uvx`
- args: ["praisonai-mcp"]
- required environment variables:
  - `OPENAI_API_KEY`: OpenAI API key. Required for agent tools and default practical use of the server. (example: `<your-openai-api-key>`)
- optional environment variables:
  - `TAVILY_API_KEY`: Tavily API key for `tavily_search` and `tavily_extract`. (example: `<your-tavily-api-key>`)
  - `EXA_API_KEY`: Exa API key for `exa_search`, `exa_search_contents`, and `exa_find_similar`. (example: `<your-exa-api-key>`)
  - `YDC_API_KEY`: You.com API key for `ydc_search` and `ydc_news`. (example: `<your-youcom-api-key>`)
  - `SEARXNG_URL`: SearxNG instance URL for `searxng_search`. (example: `<your-searxng-url>`)

Note: README also documents running the server as an SSE server with `python -m praisonai_mcp --sse --port 8080`, but no canonical client connection URL is provided. Preferred portable config is stdio via `uvx praisonai-mcp`.

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.