Self-hosted web search for LLM agents: search -> fetch -> rank pipeline with semantic caching
Webfetch is an MCP integration. Self-hosted web search for LLM agents: search -> fetch -> rank pipeline with semantic caching.
The published pypi package is webfetch-llm, version 0.1.3. Its declared MCP transport is stdio.
The package declares BRAVE_API_KEY: Optional - adds Brave to the multi-engine fusion. DDG works with no keys at all.; SERPER_API_KEY: Optional - adds Serper (Google results) to the multi-engine fusion.; TAVILY_API_KEY: Optional - adds Tavily to the multi-engine fusion.; WEBFETCH_PROVIDER: Optional - search strategy: multi (RRF fusion of available engines, default), fallback (priority failover), or a single engine name like ddg..
Check the maintainer’s instructions for account access, authentication and the supported client configuration. Once connected, inspect the tools your client receives and try a small task that matches the server’s stated purpose. The registry description does not include a verified, complete tool list.
View the publisher’s registry entry · Project repository. This profile uses version 0.1.3 from the registry. Registration identifies the publisher namespace; it does not establish that this is a first-party integration for every service it connects.
Browse related search & web scraping MCP servers for tools that cover the same kind of work.
| Variable | Description | Required |
|---|---|---|
| BRAVE_API_KEY | Optional - adds Brave to the multi-engine fusion. DDG works with no keys at all. | Optional |
| SERPER_API_KEY | Optional - adds Serper (Google results) to the multi-engine fusion. | Optional |
| TAVILY_API_KEY | Optional - adds Tavily to the multi-engine fusion. | Optional |
| WEBFETCH_PROVIDER | Optional - search strategy: multi (RRF fusion of available engines, default), fallback (priority failover), or a single engine name like ddg. | Optional |
Retrieve public web pages as readable Markdown with the reference Fetch MCP server, including pagination for longer responses.
Use Firecrawl MCP to retrieve website content and extract information for research through Firecrawl’s API-backed web tools.
An MCP (Model Context Protocol) server that makes DbbleBarrel — Singapore's rising streetwear label — discoverable by AI assistants like Claude, ChatGPT, Perplexity, and Gemini.
Ask before you fetch: will this domain serve your crawler, refuse it, or charge it?
Set up SearXNG HTTP MCP with Docker or uvx. Compare HTTP and stdio modes, configure the search instance and check optional server authentication.
Run SEO Content Machine tasks from an MCP client: scraping, crawls, Google Maps, Workspace pages.