What it does

Drives search through the Jan browser extension rather than a headless browser, which means it can reach pages behind a login you already have. That is also the risk: it operates as you, in your session. Use it for reading, not for anything that leaves a trace you would not want.

Install

Terminal

npx -y search-mcp-server

Client configuration

Paste this into your MCP client config (Claude Desktop, Cursor, or any client that reads mcpServers), then restart the client.

mcp.json

{
  "mcpServers": {
    "jan-search": {
      "command": "npx",
      "args": [
        "-y",
        "search-mcp-server"
      ]
    }
  }
}

Use it for

Searching through the browser you are already logged into

Skip it if

Headless automation; this drives a real session

When to use it

Reach for this when the task needs search inside the agent loop. Skip it if a plain shell command or a one-off script is enough — every server you add costs context and adds a failure mode.

Other TypeScript servers

Filesystem — Gives an agent scoped read, write, and search access to directories you explicitly allow
Memory — A persistent knowledge graph stored in a local JSON file, exposed through entities, relations, and observations
Sequential Thinking — Gives the model a scratchpad for structured, revisable reasoning: numbered thoughts that can branch, revise, and conclude

Jan Browser Search MCP