In-depth architectural comparison of the Brave Search MCP Server and Wet MCP MCP servers. Compare execution transports, security boundaries, tool capabilities, quality scores, and ready-to-paste client installation snippets for Claude, Cursor, Windsurf, and VS Code.
At a Glance & Executive Verdict
Brave Search MCP Server
Search & Data Extraction · Local stdio
Quality: 61/100 (Good) | Auth: API Key required
Wet MCP
Search & Data Extraction · Local stdio
Quality: 60/100 (Good) | Auth: No auth required
Verdict Summary: Choose Brave Search MCP Server if you need specialized Search & Data Extraction tools running via a local process. Choose Wet MCP if your workspace requires Search & Data Extraction integration with local subprocess execution. Both servers can be configured concurrently in your client's mcpServers manifest.
Which MCP Server Should You Choose?
Choose Brave Search MCP Server when:
You need dedicated capabilities in the Search & Data Extraction domain.
You prefer local stdio subprocess transport architecture.
Your security boundary fits: API Key required (Freemium).
You have access to required keys: BRAVE_MCP_TRANSPORT.
Web search (embedded SearXNG), content extraction, and library docs indexing with hybrid search (FTS5 + semantic). Built-in Qwen3 embedding, no API keys required.
Brave Search MCP Server is categorized under Search & Data Extraction and uses a local stdio subprocess. In contrast, Wet MCP belongs to Search & Data Extraction using local stdio subprocess. Select Brave Search MCP Server when you need capabilities focused on search & data extraction and Wet MCP when you require tools for search & data extraction.
Re-trigger the zero-config relay setup flow (prints a fresh relay URL for the browser form). Registered via `mcp-core`'s `register_open_relay_tool` so an LLM can restart setup without a manual restart.