Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/HasData/duckduckgo-mcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/hasdata/duckduckgo-mcp/ddg-baseline)<a href="https://agentmods.dev/commands/hasdata/duckduckgo-mcp/ddg-baseline"><img src="https://agentmods.dev/badge/commands/hasdata/duckduckgo-mcp/ddg-baseline/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/hasdata/duckduckgo-mcp/ddg-baseline"><img src="https://agentmods.dev/badge/commands/hasdata/duckduckgo-mcp/ddg-baseline.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00013 | $0.00294 |
| Opus 5.5 | $0.00005 | $0.00118 |
| Sonnet 5.5 | $0.00003 | $0.00059 |
| Haiku 4.5 | $0.00001 | $0.00029 |
Grade A, and why
ddg-baseline scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 23d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Take a query and report the ranking DuckDuckGo shows, as a baseline no account personalised.
Ask me for the query and the region if I have not given them. Region goes in kl, written the way DuckDuckGo writes it, such as us-en.
Then:
- Call
hasdata_duckduckgo_serp_getSearchResultswithqandkl. - List the organic results as position, title and domain, and say how many came back rather than assuming ten.
- Read the results before reporting them. DuckDuckGo fills the page whether or not anything matches, so if the entries are only loosely related, say the query has no real coverage instead of presenting them as a ranking.
- If the
adsblock is present, list the advertisers separately from the organic set so the two never blur. - If
searchAssistis present, quote it and name the sources it leans on. - Page with
nextPageTokenwhen I ask for more, and pass the token on its own with noqbeside it. Positions restart at 1 on each page, so absolute rank is the count already collected plusposition.
Do not describe this as what everyone sees, and do not compare it to another engine unless that engine's results are also in front of you.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 23d ago First seen · 19 lines · 13 tokens per session scan A e47f2f2c3363
ddg-baseline is a command published in the GitHub repository HasData/duckduckgo-mcp (7 stars, last pushed 4d ago), licensed MIT. It adds 13 tokens to every session and 294 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-23.
Other commands, from other repositories
profile-brief
A brief on a public Instagram account and what it has been posting.
hotel-shortlist
A shortlist of Booking.com hotels for a destination, dates and party.
zillow-comps
Comparable sales for an address or an area, pulled from Zillow.
hiring-map
Who is hiring for a role across several cities, with salaries where employers publish them.
tiktok-pulse
What an account posts on TikTok and which videos actually performed.
stay-shortlist
A shortlist of Airbnb stays for a destination, dates and party size.