This MCP server implements a Model Context Protocol for integrating with multiple search providers, enabling web search, local browser search, and scraping capabilities using an agent-browser.
From the registry: Web search, crawl, scrape & extract with agent-browser, SearXNG, Tavily, DuckDuckGo, Bing & more
$ npx agent-browser installPlease install the `one-search-mcp` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **Chromium-based browser** — Requires Google Chrome, Microsoft Edge, or Chromium installed for agent-browser web scraping and local search. Run: `npx agent-browser install`
Canonical MCP server config (stdio transport):
- command: `npx`
- args: ["-y","one-search-mcp"]
- optional environment variables:
- `SEARCH_PROVIDER`: Search provider: local (default, free), duckduckgo, searxng, bing, tavily, google, zhipu, exa, bocha. (example: `local`)
- `SEARCH_API_KEY`: API key for paid search providers (tavily, bing, google, etc.). (example: `<your-api-key>`)
- `SEARCH_API_URL`: SearXNG URL or Google Custom Search Engine ID. (example: `http://127.0.0.1:8080`)
Note: Default local mode is free, no API key. Docker image available with Chromium pre-installed.
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.SEARCH_API_KEYrequiredRequired for certain search providers like Tavily, Bing, Google, Zhipu, Exa, and Bocha.MCP server for searching Airweave collections with natural language queries.