# DuckDuckGo Search MCP server

> Search the web through DuckDuckGo and fetch page content as text, with no API key required.

- Listing: https://mcp.tc/i/duckduckgo
- Connect: this is a local (stdio) server; install it on your machine (see Install). The listing link is a page, not an MCP endpoint.
- Type: local (stdio)
- Auth: no API key needed
- Category: [Search & Web Data](https://mcp.tc/c/search-web)
- Vendor: nickclyde
- Repository: <https://github.com/nickclyde/duckduckgo-mcp-server>
- Package: pypi `duckduckgo-mcp-server`

## About

Connects an assistant to DuckDuckGo web search and adds a content fetching tool that downloads a page and extracts its text. Results are formatted for language models, and long result URLs are replaced with short ref:// tokens that the fetch tool accepts directly to save context.

Runs locally with uvx duckduckgo-mcp-server over stdio by default. SSE and streamable HTTP transports are also available. No sign-in or API key is needed. Optional environment variables set SafeSearch level, default region, rate limits, cache behavior, parse mode and a custom CA bundle. An opt-in curl backend can help when sites block the default HTTP client.

## What it can do

- Search the web through DuckDuckGo
- Fetch and parse webpage content into text
- Choose text, main content or markdown extraction
- Set SafeSearch level and default region
- Rate limiting for search and fetch requests
- Run over stdio, SSE or streamable HTTP

## Example prompts

- "Search DuckDuckGo for the latest Python 3.13 release notes"
- "Find recent articles about WebAssembly and summarize the top results"
- "Fetch this URL and give me the main content as markdown"
- "Look up the official docs for httpx timeouts and read the page"

## Install

### Claude Code

1. Run this in a terminal, in your project folder:

```bash
claude mcp add --transport stdio duckduckgo -- uvx duckduckgo-mcp-server
```

2. Start Claude Code and type `/mcp`. **duckduckgo** should show as connected.

Add `--scope user` to make it available in every project.

### Claude Desktop

1. Open **Settings → Developer → Edit Config**. It opens `claude_desktop_config.json`. Add:

`claude_desktop_config.json`:

```json
{
  "mcpServers": {
    "duckduckgo": {
      "command": "uvx",
      "args": [
        "duckduckgo-mcp-server"
      ]
    }
  }
}
```

2. Save the file and restart Claude Desktop.

Needs uv (Python) on your computer. The file lives in `~/Library/Application Support/Claude/` on macOS and `%APPDATA%\Claude\` on Windows.

### Cursor

[Add to Cursor](<https://cursor.com/install-mcp?name=duckduckgo&config=eyJjb21tYW5kIjoidXZ4IiwiYXJncyI6WyJkdWNrZHVja2dvLW1jcC1zZXJ2ZXIiXX0%3D>) (opens Cursor)

Or add it by hand to `~/.cursor/mcp.json` (all projects) or `.cursor/mcp.json` (this project):

`mcp.json`:

```json
{
  "mcpServers": {
    "duckduckgo": {
      "command": "uvx",
      "args": [
        "duckduckgo-mcp-server"
      ]
    }
  }
}
```

Needs uv (Python) on your computer.

### VS Code

[Install in VS Code](<https://vscode.dev/redirect/mcp/install?name=duckduckgo&config=%7B%22type%22%3A%22stdio%22%2C%22command%22%3A%22uvx%22%2C%22args%22%3A%5B%22duckduckgo-mcp-server%22%5D%7D>) (opens VS Code)

Or from a terminal:

```bash
code --add-mcp '{"name":"duckduckgo","type":"stdio","command":"uvx","args":["duckduckgo-mcp-server"]}'
```

Or commit it to the repo in `.vscode/mcp.json`:

`.vscode/mcp.json`:

```json
{
  "servers": {
    "duckduckgo": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "duckduckgo-mcp-server"
      ]
    }
  }
}
```

Needs uv (Python) on your computer.

### Devin Desktop

1. Add it to `~/.config/devin/mcp_config.json` (macOS and Linux) or `%APPDATA%\devin\mcp_config.json` (Windows):

`mcp_config.json`:

```json
{
  "mcpServers": {
    "duckduckgo": {
      "command": "uvx",
      "args": [
        "duckduckgo-mcp-server"
      ]
    }
  }
}
```

2. Refresh the MCP server list in Cascade.

Devin Desktop is the new name for Windsurf.

### Codex

```bash
codex mcp add duckduckgo -- uvx duckduckgo-mcp-server
```

Or edit `~/.codex/config.toml` directly:

`config.toml`:

```toml
[mcp_servers.duckduckgo]
command = "uvx"
args = ["duckduckgo-mcp-server"]
```

Needs uv (Python) on your computer.

### Gemini CLI

```bash
gemini mcp add duckduckgo uvx duckduckgo-mcp-server
```

This adds it to the current project. Add `-s user` to use it everywhere.

### Any client

Most clients that start local servers accept this shape:

```json
{
  "mcpServers": {
    "duckduckgo": {
      "command": "uvx",
      "args": [
        "duckduckgo-mcp-server"
      ]
    }
  }
}
```

Zed puts servers under `context_servers` in its settings, with the same `command`, `args` and `env` fields.

Needs uv (Python) on your computer.

## Details

- Server version: 0.7.0
- Last checked: 2026-10-03
- Listed: 2026-10-03
- Updated: 2026-10-03

---
Source: https://mcp.tc/i/duckduckgo (mcp.tc is an independent directory, not affiliated with this server's publisher). Corrections: https://mcp.tc/report