Does duckduckgo-mcp-server send data, and where? — data-flow verdict
provisional · AUTOMATED — forensic confirmation pending. A preliminary, fact-based flag, not a judgment that the tool is unlawful or unsafe.
100/100 integrity
100% evidence coverage
evidence-backed
Measures evidence support, not confidence — how this is scored
Verdict (the facts)
- Tool
- pip/duckduckgo-mcp-server
- Integrity axis
- undisclosed_processing — Observed behaviour matches the tool's stated function; the egress above is the tool doing its advertised job. 'honest' is the integrity axis — it does NOT imply the data flow is irrelevant; see the data-flow axis and jurisdiction.
- Data-flow axis
- Sends data to html.duckduckgo.com (US, jurisdiction tier 2) as its core function. No telemetry, analytics or error-reporting side-channel was found (full source + dependency-tree review). Where your data goes is determined by the tool's stated purpose, not by a hidden observability channel.
- Disclosure
- functional — No telemetry, analytics or error-reporting side-channel found: full source review of the PyPI sdist plus a zero-match grep across the package for all common observability SDKs (only beautifulsoup4/httpx/httpcore/mcp + optional curl_cffi). All egress is functional and neutral by purpose; egress fires on tool-call only, never on launch.
- Capture self-test
- verified
- Severity
- low — integrity axis only (undeclared exfiltration). Functional egress and disclosed metadata are reported as neutral facts and are not graded here.
- Version (pinned)
- 0.4.0 · commit
- Content hash
- sha256:a1219b83f12221964827589062658b5d0176f9251dbb516490ed48a540198f79
- Signature
- ed25519:r3hJe4em4peRcteVFSdfRJQ3Gyh4VUd23Ijhp0… · Ed25519 public key · sha256:49cf8457b42a7048
- Scanned
- 2026-06-14T00:00:00Z — Pinned to duckduckgo-mcp-server@0.4.0, published 2026-05-08. This verdict applies to that exact version; a newer release would require a re-scan.
- Re-verified
- 2026-06-14 — pinned version current
- Categories
- search functional-egress US published
- Observation history
- 1 scan(s); first seen 2026-06-14T00:00:00Z · latest 2026-06-14T00:00:00Z
Observed egress destinations
| host | country | jurisdiction | class | disclosure | frequency | kind |
| html.duckduckgo.com | US | tier 2 | functional | by purpose | during the run | search query sent to the search backend (the tool's function) |
Each destination is classified FUNCTIONAL (the tool's advertised job requires the call — a neutral fact about where your data goes), SESSION/AUTH (handshake with the same operator), or TELEMETRY/ERROR_REPORTING (an observability side-channel not required for the function). Disclosure is judged across the tool's full public doc surface, not just its README, and any 'undisclosed telemetry' finding is adversarially refuted before it is asserted.
Jurisdiction context: Tier 2 = third country (e.g. US): transferring EU personal data to a third country requires a transfer basis under GDPR Art. 44-49 (e.g. SCCs / EU-US Data Privacy Framework) — an obligation on you, the deployer; the tool gives no control over this flow. This is the applicable framework, not a finding that the tool violates it.
Evidence — the captured request (verify, don't just trust)
Capture self-test: verified — a beacon decoy was emitted from the tool's network context; its presence in the intercept means a 'no egress' result would have been trustworthy.
Observed: POST
https://html.duckduckgo.com/html ×1
— intercepted (the tool's HTTPS was terminated against the sandbox CA; the egress was then blocked by strict-egress, but the full request was captured)
Payload fields actually sent:
Captured payload sample (one event):
q=FILE-CONTENT%3A%3Acanary-03320ce1-file-b0bf83629c04%3A%3AEND&b=&kl=FILE-CONTENT%3A%3Acanary-03320ce1-file-b0bf83629c04%3A%3AEND&kp=-1
Captured in the sandbox run. The distinct_id (a persistent machine identifier) and the write-only, public-by-design ingestion key are truncated above; payload_fields is the union observed across the run.
Reproduce it yourself (canary-sandbox (open methodology; Docker backend)):
python -m canary.cli scan <target> --backend docker # target: pip duckduckgo-mcp-server@0.4.0
Re-run it yourself: the scanner installs the pinned version, drives the tool over MCP, and intercepts all egress.
Full raw captured trace + verification:
/verdict/duckduckgo/evidence.json
— every captured request (redacted), the verdict content-hash and the package checksum, for an AI or auditor that wants the underlying observation, not just the conclusion.
Disclosure check (the §824 evidence)
- Read
- PyPI sdist source (full review); dependency tree grep (zero observability-SDK matches); README
- Quoted from the tool's own docs
- “”
- Match
- No telemetry, analytics or error-reporting side-channel found: full source review of the PyPI sdist plus a zero-match grep across the package for all common observability SDKs (only beautifulsoup4/httpx/httpcore/mcp + optional curl_cffi). All egress is functional and neutral by purpose; egress fires on tool-call only, never on launch.
- Residual gap
- The README never states 'no telemetry' in the tool's own voice — this is 'no telemetry side-channel found on review', not a vendor guarantee.
How we know this — claims by basis
A verdict is a reproducible evidence container, not just a claim. Each assertion is tagged: an observation is in the capture and reproducible; an inference is our reasoning over it; documented is the tool’s own statement; a classification is our adversarially-reviewed judgment. Observation never reads as inference.
Observed — directly in the capture, reproducible
- The tool sent 1 request(s) to html.duckduckgo.com. — Captured in the sandbox run (published redacted in the evidence artifact); re-run the scan to reproduce. (confidence: high)
Classified — our adversarially-reviewed judgment
- html.duckduckgo.com is classified as functional (required for the tool's advertised function). — Adversarially reviewed. (confidence: high)
- Disclosure status: functional. — No telemetry, analytics or error-reporting side-channel found: full source review of the PyPI sdist plus a zero-match grep across the package for all common observability SDKs (only beautifulsoup4/httpx/httpcore/mcp + op (confidence: high)
Method
Installed and run in an isolated container; fed traceable decoy data; all outbound traffic intercepted (TLS broken via own CA, iptables transparent redirect). Endpoints, resolved geo/jurisdiction and frequency are observed facts. Capture self-test passed.
Scope
Compares the tool's declared destinations against what was observed in one sandbox run. Checks transparency / integrity for a cooperative tool, NOT resistance to deliberate evasion. "honest"/"clean" means "observed without deviation within our reach", NOT "guaranteed no hidden egress".
Out of scope: exfiltration split/chunked across requests; tool-side encryption of the payload before egress; input/time/state-triggered processing not triggered in the run.
Machine-readable verdict: /verdict/duckduckgo.json.
This page describes observed behaviour and its relation to the tool's own disclosures — it is not a legal judgment.
Search context: does duckduckgo-mcp-server send data, duckduckgo-mcp-server privacy, duckduckgo-mcp-server data flow, duckduckgo-mcp-server telemetry, where does duckduckgo-mcp-server send data, is duckduckgo-mcp-server safe, what data does duckduckgo-mcp-server collect, how to disable duckduckgo-mcp-server telemetry, duckduckgo-mcp-server opt out tracking, duckduckgo-mcp-server GDPR data residency, duckduckgo-mcp-server third-party / jurisdiction.