Wet MCP runs on your own machine — the client starts it, so there is no endpoint to ping. 3 069 installs a week from pypi. Last commit 17 Sep 2026.
Open-source MCP server for AI agents: web search, content extraction, and library docs.
We read the source, 18 h ago · rules 3dff92dd89df
Found in continuous integration, deployment or infrastructure files, or in a neighbouring package of the same monorepo. None of this is installed when you add the server: it describes how the project is built and released. We list it because a leaked key in a build pipeline is still a real problem, but it is not something this server does on your machine.
- name: File or update the canary failure issue
env:
GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
Today is the operative word: we check Wet MCP every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add wet-mcp -- uvx wet-mcp
{
"mcpServers": {
"wet-mcp": {
"args": [
"wet-mcp"
],
"command": "uvx"
}
}
}
[mcp_servers.wet-mcp]
command = "uvx"
args = ["wet-mcp"]
{
"mcpServers": {
"wet-mcp": {
"args": [
"wet-mcp"
],
"command": "uvx"
}
}
}
{
"mcpServers": {
"wet-mcp": {
"args": [
"wet-mcp"
],
"command": "uvx"
}
}
}
This one needs environment variables set before it will start:
API_KEYS (Provider API keys (format: PROVIDER_API_KEY:key,...). Select models per task with EMBEDDING_MODELS / RERANK_MODELS / LLM_MODELS (CSV provider/model, order = litellm fallback); provider is inferred from the model prefix. Empty embedding/rerank chain falls back to fastretrieval's built-in local reference model.), GITHUB_TOKEN (GitHub personal access token for higher rate limits on library discovery).
The author declared them in the registry entry; get the values from the project itself.
FastMCP server for Tavily search API with web search and content extraction
Rust MCP server for denoised web search — fetch, clean, and rerank web content for AI agents.
Rust MCP server for denoised web search — fetch, clean, and rerank web content for AI agents.
Rust MCP server for denoised web search — fetch, clean, and rerank web content for AI agents.
Web search, AI agent, and content extraction via You.com APIs
Free open-source web search and page reading for LLMs, AI agents, and RAG.
AI-powered web research MCP server for agents. Supports web search, browse page, extract...
Fully local MCP server and CLI for web research
Answers built from our own checks of this server.