webfetch for Windsurf
io.github.firish/webfetch
Self-hosted web search for LLM agents: search -> fetch -> rank pipeline with semantic caching
client:Windsurf
transport:stdio
runtime:pypi
Install webfetch in Windsurf
~/.codeium/windsurf/mcp_config.json · windows: %USERPROFILE%\.codeium\windsurf\mcp_config.json
{
"mcpServers": {
"webfetch": {
"command": "uvx",
"args": [
"webfetch-llm"
],
"env": {
"BRAVE_API_KEY": "<BRAVE_API_KEY>",
"SERPER_API_KEY": "<SERPER_API_KEY>",
"TAVILY_API_KEY": "<TAVILY_API_KEY>",
"WEBFETCH_PROVIDER": "<WEBFETCH_PROVIDER>"
}
}
}
}Global only — Windsurf has no per-project MCP config. Refresh Cascade after saving. Windsurf docs