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.

Quick Start

uvx duckduckgo-mcp-server

Related MCP server: duck-poacher-mcp

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 that fetch_content accepts 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

1. Download Claude Desktop

2. 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": ["duckduckgo-mcp-server"],
            "env": {
                "DDG_SAFE_SEARCH": "STRICT",
                "DDG_REGION": "cn-zh"
            }
        }
    }
}

Configuration Options:

• DDG_SAFE_SEARCH: SafeSearch filtering level (optional)

  • STRICT: Maximum content filtering (kp=1)

  • MODERATE: Balanced filtering (kp=-1, default if not specified)

  • OFF: No content filtering (kp=-2)

• DDG_REGION: Default region/language code (optional, examples below)

  • us-en: United States (English)

  • cn-zh: China (Chinese)

  • jp-ja: Japan (Japanese)

  • wt-wt: No specific region

  • Leave empty for DuckDuckGo's default behavior

• DDG_CA_CERTS: Path to a PEM CA bundle used to verify TLS certificates on outbound requests (optional). Needed behind TLS-intercepting proxies — see Running behind a TLS-intercepting proxy.

• DDG_RATE_LIMIT_STRATEGY: sliding (default, historical 60s window) or token_bucket (burst, then smooth).

• DDG_SEARCH_RPM: Search requests per minute (default: 30).

• DDG_FETCH_RPM: Global fetch_content requests per minute (default: 20).

• DDG_FETCH_HOST_RPM: Optional per-host fetch cap (default: 0, off). Set a positive number to enable.

• DDG_CACHE_TTL: Seconds to keep a parsed page in the in-memory fetch_content cache (default: 300). Paginated reads of the same URL reuse one download. Set 0 to disable.

• DDG_CACHE_MAX_ENTRIES: Maximum pages kept in that cache (default: 64). Least-recently-used eviction. Set 0 to disable.

• DDG_PARSE_MODE: Default fetch_content extractor (text, main, or markdown). Default is text (historical flattened page). Per-call parse_mode overrides this.

• DDG_REF_URL_THRESHOLD: Search-result URLs longer than this many characters are replaced with short ref://<id> tokens (default: 120). Set 0 to always show full URLs. Also --ref-url-threshold.

3. Restart Claude Desktop

Running with Claude Code

1. Download Claude Code

2. Ensure uvenv is installed and the uvx command is available

3. Add the MCP server: claude mcp add ddg-search uvx duckduckgo-mcp-server

Running with SSE or Streamable HTTP

The server supports alternative transports for use with other MCP clients:

# SSE transport
uvx duckduckgo-mcp-server --transport sse

# Streamable HTTP transport
uvx duckduckgo-mcp-server --transport streamable-http

The default transport is stdio, which is used by Claude Desktop and Claude Code.

When running with sse or streamable-http, override the default bind address (127.0.0.1:8000) with the --host and --port flags:

uvx duckduckgo-mcp-server --transport streamable-http --host 0.0.0.0 --port 7070

Running behind a reverse proxy or in Docker

The MCP SDK enables DNS-rebinding protection for the HTTP transports and, by default, only accepts Host/Origin headers for localhost. Behind a reverse proxy or in a container the client's Host header won't match, so requests fail with 421 Misdirected Request.

Fix it by allow-listing the host(s) and origin(s) clients actually use (preferred over disabling protection). Values support host, host:port, and wildcard-port host:*:

uvx duckduckgo-mcp-server --transport streamable-http --host 0.0.0.0 --port 7070 \
  --allowed-hosts ddg-mcp.example.com "ddg-mcp.example.com:*" \
  --allowed-origins "https://ddg-mcp.example.com"

Equivalent environment variables (comma-separated) are also available: DDG_ALLOWED_HOSTS, DDG_ALLOWED_ORIGINS.

As a last resort you can turn the check off entirely with --disable-dns-rebinding-protection (or DDG_DISABLE_DNS_REBINDING_PROTECTION=1). Prefer an allow-list — disabling protection removes a defense against DNS-rebinding attacks. When nothing is configured, the secure localhost-only default is preserved.

Running behind a TLS-intercepting proxy

Corporate proxies that re-sign HTTPS traffic with their own CA (via HTTPS_PROXY) cause outbound requests to fail with certificate verification errors, because the HTTP clients don't trust the proxy's self-signed CA (and httpx no longer reads the SSL_CERT_FILE environment variable). Point the server at your proxy's CA bundle:

uvx duckduckgo-mcp-server --ca-certs /path/to/proxy-ca.pem

Or set DDG_CA_CERTS=/path/to/proxy-ca.pem. The bundle is used by both the search and fetch_content tools, on the httpx and curl backends alike.

As a last resort, --no-ssl-verify (or DDG_SSL_VERIFY=0) disables certificate verification entirely. This exposes traffic to interception by anyone on the network path — prefer --ca-certs.

Backends (bypassing bot detection)

Some sites — and, as of recently, DuckDuckGo's own search endpoint (html.duckduckgo.com) — block the default httpx client because of its distinctive TLS fingerprint, regardless of User-Agent. Cloudflare Bot Management and similar filters key on the JA3/TLS handshake, not on headers, so html.duckduckgo.com may answer httpx with an empty HTTP 202 page (silently yielding "no results"). An opt-in backend, curl (implemented via curl_cffi), impersonates a real Chrome browser's TLS handshake and passes through those checks.

Both the search tool and the fetch_content tool support these backends.

Installation:

# Default install (httpx only)
uv pip install duckduckgo-mcp-server

# With the optional browser backend
uv pip install "duckduckgo-mcp-server[browser]"

Backend options:

Two ways to configure the backend:

1. Server-wide default via the --fetch-backend CLI flag (applies to every fetch_content call):

   # Default behavior — uses httpx
   uvx duckduckgo-mcp-server
   
   # Force curl for every fetch (requires the [browser] extra)
   uvx --with "duckduckgo-mcp-server[browser]" duckduckgo-mcp-server --fetch-backend curl
   
   # Try httpx first, fall back to curl on 403 / Cloudflare challenge
   uvx --with "duckduckgo-mcp-server[browser]" duckduckgo-mcp-server --fetch-backend auto

2. Per-call override via the backend argument on the fetch_content tool (overrides the CLI default for that single call). The tool exposes backend in its input schema, so an MCP client can choose "httpx", "curl", or "auto" on a fetch-by-fetch basis.

For fetch_content, the default stays httpx so users who don't need the impersonation don't pay for the extra dependency.

Search backend

Because DuckDuckGo's search endpoint now fingerprint-blocks plain httpx, the search tool defaults to auto: it tries httpx first and falls back to curl when it detects a block (HTTP 202/403). The fallback only works if the [browser] extra is installed; otherwise search returns a message telling you to install it.

Configure the search backend with the --search-backend CLI flag or the DDG_SEARCH_BACKEND environment variable (auto (default) / httpx / curl):

# Recommended: install the browser extra so the auto fallback can impersonate Chrome
uvx --with "duckduckgo-mcp-server[browser]" duckduckgo-mcp-server

# Force curl for every search
uvx --with "duckduckgo-mcp-server[browser]" duckduckgo-mcp-server --search-backend curl

# Opt out of the fallback (legacy behavior — may return no results while blocked)
uvx duckduckgo-mcp-server --search-backend httpx

Development

For local development:

# Install dependencies
uv sync

# Run with the MCP Inspector
mcp dev src/duckduckgo_mcp_server/server.py

# Install locally for testing with Claude Desktop
mcp install src/duckduckgo_mcp_server/server.py

# Run all tests
uv run python -m pytest src/duckduckgo_mcp_server/ -v

# Run only unit tests
uv run python -m pytest src/duckduckgo_mcp_server/test_server.py -v

# Run only e2e tests
uv run python -m pytest src/duckduckgo_mcp_server/test_e2e.py -v

Available Tools

1. Search Tool

async def search(query: str, max_results: int = 10, region: str = "") -> str

Performs a web search on DuckDuckGo and returns formatted results.

Parameters:

• query: Search query string

• max_results: Maximum number of results to return (default: 10)

• region: (Optional) Region/language code to override the default. Leave empty to use the configured default region.

Region Code Examples:

• us-en: United States (English)

• cn-zh: China (Chinese)

• jp-ja: Japan (Japanese)

• de-de: Germany (German)

• fr-fr: France (French)

• wt-wt: No specific region

Returns: Formatted string containing search results with titles, URLs, and snippets.

Example Usage:

• Search with default settings: search("python tutorial")

• Search with specific region: search("latest news", region="jp-ja") for Japanese news

2. Content Fetching Tool

async def fetch_content(
    url: str,
    start_index: int = 0,
    max_length: int = 8000,
    backend: Optional[str] = None,
    parse_mode: Optional[str] = None,
) -> str

Fetches and parses content from a webpage.

Parameters:

• url: The webpage URL to fetch content from, or a ref://<id> token from search results

• start_index: Character offset to start reading from (for pagination)

• max_length: Maximum number of characters to return

• backend: Optional per-call override of the default fetch backend ("httpx", "curl", or "auto"). When omitted, uses whatever was set via --fetch-backend at server startup.

• parse_mode: Optional per-call extractor ("text", "main", or "markdown"). When omitted, uses DDG_PARSE_MODE / --parse-mode (default text).

Returns: Cleaned and formatted text content from the webpage. The parsed full page is cached in memory (default 5 minutes) so later pages via start_index do not re-download. Metadata includes cache=hit or cache=miss when the cache is enabled.

SSRF protection: By default fetch_content refuses URLs that resolve to loopback, private (RFC1918), link-local (including the 169.254.169.254 cloud metadata endpoint), reserved, multicast, or unspecified addresses, and it re-validates every redirect hop. Only http/https URLs are allowed. For trusted local deployments that need to fetch internal hosts, disable the guard with DDG_ALLOW_PRIVATE_URLS=1 or --allow-private-urls. See SECURITY.md for details.

3. Link Expansion Tool

async def expand_link(token: str) -> str

Search results replace URLs longer than DDG_REF_URL_THRESHOLD characters (default 120) with short, stable ref://<id> tokens so long tracking-laden links do not eat context. fetch_content accepts a token in place of a URL, so the model only needs this tool when it has to show or cite the real link.

Parameters:

• token: A ref://<id> token exactly as it appeared in search results (the bare id also works)

Returns: The full original URL, or an error if the token is unknown. Tokens live in memory for the lifetime of the server process (bounded by an LRU cap), so they are forgotten on restart.

Features in Detail

Rate Limiting

• Search: 30 requests per minute by default (DDG_SEARCH_RPM / --search-rpm)

• Content fetching: 20 requests per minute globally (DDG_FETCH_RPM / --fetch-rpm)

• Optional per-host fetch cap, off by default (DDG_FETCH_HOST_RPM / --fetch-host-rpm)

• Strategies: sliding (default) or token_bucket via DDG_RATE_LIMIT_STRATEGY / --rate-limit-strategy

• HTTP 429 responses honor Retry-After (capped at 30s) and retry once

• Cache hits on fetch_content skip both the download and the fetch rate limiter

Content cache

• In-memory TTL cache of the fully parsed page (before pagination)

• Default TTL 300 seconds, 64 entries, least-recently-used eviction

• Errors are never cached

• Configure with DDG_CACHE_TTL / DDG_CACHE_MAX_ENTRIES or --cache-ttl / --cache-max-entries

• Set either value to 0 to disable

Result Processing

• Removes ads and irrelevant content

• Cleans up DuckDuckGo redirect URLs

• Formats results for optimal LLM consumption

• Truncates long content appropriately

Content parsing modes

fetch_content accepts parse_mode:

Content Safety

• SafeSearch Filtering: Configured at server startup via DDG_SAFE_SEARCH environment variable

  • Controlled by administrators, not modifiable by AI assistants

  • Filters inappropriate content based on the selected level

  • Uses DuckDuckGo's official kp parameter

• Region Localization:

  • Default region set via DDG_REGION environment variable

  • Can be overridden per search request by AI assistants

  • Improves result relevance for specific geographic regions

Error Handling

• Comprehensive error catching and reporting

• Detailed logging through MCP context

• Graceful degradation on rate limits or timeouts

Contributing

Issues and pull requests are welcome!

License

This project is licensed under the MIT License.

Star History