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/rules/hasdata/duckduckgo-mcp/hasdata-duckduckgo)<a href="https://agentmods.dev/rules/hasdata/duckduckgo-mcp/hasdata-duckduckgo"><img src="https://agentmods.dev/badge/rules/hasdata/duckduckgo-mcp/hasdata-duckduckgo/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/rules/hasdata/duckduckgo-mcp/hasdata-duckduckgo"><img src="https://agentmods.dev/badge/rules/hasdata/duckduckgo-mcp/hasdata-duckduckgo.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 | $0.00018 | $0.00512 |
| Opus 5.5 | $0.00007 | $0.00205 |
| Sonnet 5.5 | $0.00004 | $0.00102 |
| Haiku 4.5 | $0.00002 | $0.00051 |
Grade A, and why
hasdata-duckduckgo 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 3d 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.
How it starts
The opening of the file, as written. The whole thing — 33 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DuckDuckGo through HasData
One tool, hasdata_duckduckgo_serp_getSearchResults. Nothing is strictly required, but a call needs either q or a nextPageToken. Sending neither returns 422 naming both fields, because the requirement is conditional.
Targeting
kl is the region in DuckDuckGo's own notation, such as us-en or de-de. cc is the country and setLang the language, and kl takes precedence over both, so setting all three means the last two do nothing.
DuckDuckGo does not personalise by account, so a result set is not shaped by anyone's history. That makes it closer to a neutral baseline than a tailored engine, which is not the same as a promise that two calls return an identical ranking.
There is no empty result
A query with nothing behind it still comes back full. A nonsense string returns ten loosely related entries and nothing in the payload marks them as a miss, so code that waits for an empty array waits forever. Judge relevance yourself, and say when the results do not actually answer the query.
The keys are organicResults, ads, searchAssist and pagination. Any of the middle two can be absent rather than empty, so test for the key before reading it.
Positions are per page
position counts inside the response it came from, and page two starts at 1 again. Page size is not fixed either, and pages of ten and fifteen both turn up, so absolute rank is the number of results already collected plus position.
Page with nextPageToken and pass it alone. The token carries the query and the offset, and sending a fresh q beside it does not error. The token wins silently, so the answer is the old query's next page while the log says you searched for something else.
Each successful call spends credits from the connected account.
Prompts and resources
The server also serves resources that spell out the accepted values of every parameter that takes a fixed list, each one at hasdata://duckduckgo/<parameter>. Reading one spends no credits and makes no upstream request, which beats discovering the vocabulary from a rejected call. Listing them needs no API key either, so a client can read them before the user has connected an account.
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.
- 3d ago Changed · +4 lines ec0c715ec908
- 23d ago First seen · 29 lines · 18 tokens per session scan A b5f1a52d4c39
hasdata-duckduckgo is a cursor rule published in the GitHub repository HasData/duckduckgo-mcp (7 stars, last pushed 3d ago), licensed MIT. It adds 18 tokens to every session and 512 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 cursor rules, from other repositories
hasdata-instagram
How to pull public Instagram profiles and post feeds through the HasData MCP server.
hasdata-booking
How to pull Booking.com hotel search and property details through the HasData MCP server.
hasdata-zillow
How to pull Zillow listings and property details through the HasData MCP server.
hasdata-indeed
How to pull Indeed job listings and postings through the HasData MCP server.
hasdata-tiktok
How to pull TikTok profiles, post feeds, keyword search and comments through the HasData MCP server.
hasdata-airbnb
How to pull Airbnb stays and listing details through the HasData MCP server.