Home › Search & Research › wet

wet

Open-source MCP server for AI agents: web search, content extraction, and library docs.

Python CloudLocal macOSWindowsLinux

★ 24 stars Last pushed 2026-11-11 License: Apache-2.0

View repository →

Connect

Review any command before running it. Package names and URLs come from the server's own registry entry.

Package (pypi 3.20.0)

uvx wet-mcp

Or add to your MCP client config:

{
  "mcpServers": {
    "wet": {
      "command": "uvx",
      "args": [
        "wet-mcp"
      ],
      "env": {
        "OPENROUTER_API_KEY": "<YOUR_VALUE>",
        "GITHUB_TOKEN": "<YOUR_VALUE>"
      }
    }
  }
}

OPENROUTER_API_KEY secret — OpenRouter API key — the single default credential for the [models.embed|rerank|chat|jev_score] provider cells and the openrouter search backend. Per-task overrides live in ~/.wet/config.toml; keys may also be injected via HULL_EMBED_API_KEY / HULL_RERANK_API_KEY / HULL_CHAT_API_KEY / HULL_JEV_SCORE_API_KEY. Empty cells fall back to local ONNX models.
GITHUB_TOKEN secret — GitHub personal access token for higher rate limits on library discovery