What it does

Web and news search through DuckDuckGo, which means no API key and no query history tied to an account. The output is what a search engine returns: titles, URLs, snippets. Whether that is useful depends on whether the agent can then fetch the pages — this server alone does not.

Install

Terminal

npx -y @ericthered926/duckduckgo-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": {
    "duckduckgo": {
      "command": "npx",
      "args": [
        "-y",
        "@ericthered926/duckduckgo-mcp-server"
      ]
    }
  }
}

Use it for

Search results without handing queries to an ad-funded engine

Skip it if

Research needing depth; DDG returns links, not answers

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

DuckDuckGo MCP