DuckDuckGo SearchSAFE
A Model Context Protocol (MCP) server that provides web search capabilities through DuckDuckGo, with additional features for content fetching and parsing.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
[](https://pypi.org/project/duckduckgo-mcp-server/) [](https://pypi.org/project/duckduckgo-mcp-server/) [](https://pypi.org/project/duckduckgo-mcp-server/)
A Model Context Protocol (MCP) server that provides web search capabilities through DuckDuckGo, with additional features for content fetching and parsing.
Quick Start
uvx duckduckgo-mcp-server
Features
- Web Search: Search DuckDuckGo with advanced rate limiting and result formatting
- Content Fetching: Retrieve and parse webpage content with intelligent text extraction
- Long URL Shortening: Over-long result URLs become short
ref://tokens thatfetch_contentaccepts directly, saving context - Rate Limiting: Built-in protection against rate limits for both search and content fetching
- Error Handling: Comprehensive error handling and logging
- LLM-Friendly Output: Results formatted specifically for large language model consumption
Installation
Install from PyPI using uv:
uv pip install duckduckgo-mcp-server
Usage
Running with Claude Desktop
- Download Claude Desktop
- Create or edit your Claude Desktop configuration:
- On macOS:
~/Library/Application Support/Claude/claude_desktop_config.json - On Windows:
%APPDATA%\Claude\claude_desktop_config.json
Add the following configuration:
Basic Configuration (No SafeSearch, No Default Region):
{
"mcpServers": {
"ddg-search": {
"command": "uvx",
"args": ["duckduckgo-mcp-server"]
}
}
}With SafeSearch and Region Configuration:
{
"mcpServers": {
"ddg-search": {
"command": "uvx",
"args": ["duckdu1ca9b5a1444bOBSERVED · 2026-09-24Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control.
claude mcp add duckduckgo-mcp-server -- uvx duckduckgo-mcp-server
{
"mcpServers": {
"duckduckgo-mcp-server": {
"command": "uvx",
"args": [
"duckduckgo-mcp-server"
]
}
}
}Exposed tools (3)
3 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
expand_link | read | Expand a shortened ref://<id> link token from search results back into the full URL. Search results replace very long URLs with short ref:// tokens to save space. fetch_content accepts those tokens directly, so only call this when you need the real URL, for example to show or cite a link to the user |
fetch_content | read | Fetch and extract the main text content from a webpage. Strips out navigation, headers, footers, scripts, and styles to return clean readable text. Use this after searching to read the full content of a specific result. Supports pagination for long pages via start_index and max_length. Repeated or p |
search | read | Search the web using DuckDuckGo. Returns a list of results with titles, URLs, and snippets. Use this to find current information, research topics, or locate specific websites. For best results, use specific and descriptive search queries. |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- declared (10 observation(s))
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (10)
> loopback, private (RFC1918), link-local (including the `169.254.169.254` cloud
`169.254.169.254` cloud metadata endpoint), reserved, multicast, and unspecified
self._assert_blocked("http://169.254.169.254/latest/meta-data/")fetcher.fetch_and_parse("http://169.254.169.254/latest/meta-data/", DummyCtx())return f"http://127.0.0.1:{server.server_address[1]}"url = f"http://127.0.0.1:{server.server_address[1]}"self._assert_blocked("http://127.0.0.1/")self._assert_blocked("http://127.0.0.1:8080/latest/meta-data/")self._assert_blocked("http://169.254.169.254/latest/meta-data/")fetcher = WebContentFetcher(allow_private_urls=True, ssl_verify=False)
Gates applied: no_behavioural_pass.
1ca9b5a1444bfull audit observations/trust-audit/mcp-server/nickclyde__duckduckgo-search-3.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-09-24 | 1ca9b5a1444b | SAFE | B | 89 | first audit |
Questions
What is the DuckDuckGo Search MCP server?
A Model Context Protocol (MCP) server that provides web search capabilities through DuckDuckGo, with additional features for content fetching and parsing.
What tools does DuckDuckGo Search expose?
3 in total: 3 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is DuckDuckGo Search safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does DuckDuckGo Search need?
No credential environment variables were found in its source, so it appears to need none.
How does DuckDuckGo Search run?
It speaks stdio and streamable-http, so it runs as a local process your client starts. It is published on PyPI as duckduckgo-mcp-server.
How current is this page?
The grade is for one exact copy of the source (1ca9b5a1444b), read on 2026-09-24. The repository is watched and re-audited when it changes.