webfetch for VS Code
io.github.firish/webfetch
Self-hosted web search for LLM agents: search -> fetch -> rank pipeline with semantic caching
client:VS Code
transport:stdio
runtime:pypi
Install webfetch in VS Code
.vscode/mcp.json
{
"inputs": [
{
"type": "promptString",
"id": "brave-api-key",
"description": "BRAVE_API_KEY",
"password": true
},
{
"type": "promptString",
"id": "serper-api-key",
"description": "SERPER_API_KEY",
"password": true
},
{
"type": "promptString",
"id": "tavily-api-key",
"description": "TAVILY_API_KEY",
"password": true
},
{
"type": "promptString",
"id": "webfetch-provider",
"description": "WEBFETCH_PROVIDER",
"password": true
}
],
"servers": {
"webfetch": {
"type": "stdio",
"command": "uvx",
"args": [
"webfetch-llm"
],
"env": {
"BRAVE_API_KEY": "${input:brave-api-key}",
"SERPER_API_KEY": "${input:serper-api-key}",
"TAVILY_API_KEY": "${input:tavily-api-key}",
"WEBFETCH_PROVIDER": "${input:webfetch-provider}"
}
}
}
}VS Code prompts for each input the first time the server starts, so no secret is written to the file. VS Code docs