DDGS

Metasearch Python library that aggregates results from multiple search engines (Bing, Brave, DuckDuckGo, Google, Mojeek, Yandex, Yahoo, Wikipedia) into a unified interface. Supports text, image, video, news, and book searches. Includes an MCP server with HTTP and SSE transports, plus a standalone API server.

Evaluated Mar 07, 2026 (0d ago) vunknown
Homepage ↗ Repo ↗ AI & Machine Learning search metasearch duckduckgo google bing brave mcp web-search news-search image-search video-search
⚙ Agent Friendliness
70
/ 100
Can an agent use this?
🔒 Security
68
/ 100
Is it safe for agents?
⚡ Reliability
63
/ 100
Does it work consistently?

Score Breakdown

⚙ Agent Friendliness

MCP Quality
65
Documentation
70
Error Messages
45
Auth Simplicity
88
Rate Limits
65

🔒 Security

TLS Enforcement
90
Auth Strength
65
Scope Granularity
55
Dep. Hygiene
72
Secret Handling
58

DuckDuckGo search MCP. No API key needed. Privacy-preserving search. No tracking of queries. Low security risk. Rate limits enforced informally.

⚡ Reliability

Uptime/SLA
65
Version Stability
65
Breaking Changes
60
Error Recovery
62
AF Security Reliability

Best When

You need free, multi-engine web search for AI agents without paying per-query API fees to commercial search providers.

Avoid When

You need guaranteed uptime, official API access with SLAs, or very high query volumes. Commercial search APIs (Tavily, Brave Search API) may be more reliable.

Use Cases

  • AI agent web search via MCP without per-query API costs
  • Aggregated multi-engine search for better coverage
  • News monitoring and research across multiple sources
  • Image and video search for AI workflows
  • Book discovery via Anna's Archive integration

Not For

  • High-volume production search (may hit rate limits from upstream engines)
  • Guaranteed search result freshness or completeness
  • Enterprise search with SLAs

Interface

REST API
Yes
GraphQL
No
gRPC
No
MCP Server
Yes
SDK
Yes
Webhooks
No

Authentication

OAuth: No Scopes: No

No authentication required. Uses upstream search engines directly without API keys. Proxy support available for rate limit avoidance.

Pricing

Model: open_source
Free tier: Yes
Requires CC: No

MIT license. Completely free. Relies on scraping/unofficial access to search engines, which may break without notice.

Agent Metadata

Pagination
max-results
Idempotent
Full
Retry Guidance
Not documented

Known Gotchas

  • Relies on unofficial/scraping access to search engines - may break without notice
  • Rate limits are opaque and depend on upstream engines
  • Results quality and availability varies by backend engine
  • MCP server requires running the API server separately (Docker or shell script)
  • Book search uses Anna's Archive which has legal/availability concerns in some jurisdictions

Alternatives

Full Evaluation Report

Comprehensive deep-dive: security analysis, reliability audit, agent experience review, cost modeling, competitive positioning, and improvement roadmap for DDGS.

AI-powered analysis · PDF + markdown · Delivered within 30 minutes

$99

Package Brief

Quick verdict, integration guide, cost projections, gotchas with workarounds, and alternatives comparison.

Delivered within 10 minutes

$3

Score Monitoring

Get alerted when this package's AF, security, or reliability scores change significantly. Stay ahead of regressions.

Continuous monitoring

$3/mo

Scores are editorial opinions as of 2026-03-07.

6470
Packages Evaluated
26150
Need Evaluation
173
Need Re-evaluation
Community Powered