Does @upstash/context7-mcp 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.

Verdict (the facts)

Tool

npm/@upstash/context7-mcp

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 context7.com (US, jurisdiction tier 2) as its core function; analytics metadata rides on the same functional request (disclosure: disclosed). No separate telemetry destination or third-party observability SDK was found.

Disclosure

disclosed — Sole functional egress is to context7.com (/api/v2 search + context) — sending the query plus libraryName/libraryId is the docs-lookup function; calls fire on tool-call only, never on launch. No third-party telemetry SDK. Riding on the same functional request is a bundle of X-Context7-* metadata headers (client IDE name/version, transport type, server version, an AES-256-CBC-encrypted client IP used only in HTTP-server mode, and an opaque session UUID) — a same-host piggybacked analytics side-channel, not a separate destination. This metadata is publicly disclosed on Context7's 'Data Privacy' docs page ('What is sent to the Context7 API').

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)

3.2.1 · commit

Content hash

sha256:9cc943487f1b94c9e400c47390f32b142b2df53d81088a016c75299fb932df3b

Signature

ed25519:T4ZrdYdRw/Nd2TIm0z/XO7ijzCmzzBw7xd1X8I… · Ed25519 public key · sha256:49cf8457b42a7048

Scanned

2026-06-14T00:00:00Z — Pinned to @upstash/context7-mcp@3.2.1, published 2026-06-13. This verdict applies to that exact version; a newer release would require a re-scan.

Re-verified

2026-06-14 — pinned version current

Categories

docs-knowledge 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

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: GET https://context7.com/api/v2/libs/search?query=FILE-CONTENT%3A%3Acanary-e7cedde3-file-348df583f222%3A%3AEND&libraryName=Canary+canary-e7cedde3-name-bf442d5870c0 ×2 — 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):

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: npm @upstash/context7-mcp@3.2.1
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/context7/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

Context7 'Data Privacy' docs page (verified live); package source (header construction)

Quoted from the tool's own docs

“Context7 'Data Privacy' page enumerates: MCP client name/version (for analytics), transport type, and an AES-256-CBC-encrypted client IP (for rate limiting).”

Match

Sole functional egress is to context7.com (/api/v2 search + context) — sending the query plus libraryName/libraryId is the docs-lookup function; calls fire on tool-call only, never on launch. No third-party telemetry SDK. Riding on the same functional request is a bundle of X-Context7-* metadata headers (client IDE name/version, transport type, server version, an AES-256-CBC-encrypted client IP used only in HTTP-server mode, and an opaque session UUID) — a same-host piggybacked analytics side-channel, not a separate destination. This metadata is publicly disclosed on Context7's 'Data Privacy' docs page ('What is sent to the Context7 API').

Residual gap

The docs do not print the literal header names (X-Context7-Source / X-Context7-Server-Version) or mention mcp-session-id, so disclosure is substantively complete but not header-for-header exhaustive. Auth hosts (clerk.context7.com, login.microsoftonline.com) and Upstash Redis are HTTP-server-mode only and dormant for the default local stdio path.

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 2 request(s) to context7.com. — Captured in the sandbox run (published redacted in the evidence artifact); re-run the scan to reproduce. (confidence: high)

Documented — the tool's own statement

• The tool's own docs state (quoted): Context7 'Data Privacy' page enumerates: MCP client name/version (for analytics), transport type, and an AES-256-CBC-encrypted client IP (for rate limiting). — Context7 'Data Privacy' docs page (verified live); package source (header construction) (confidence: high)

Classified — our adversarially-reviewed judgment

• context7.com is classified as functional (required for the tool's advertised function). — Adversarially reviewed. (confidence: high)
• Disclosure status: disclosed. — Sole functional egress is to context7.com (/api/v2 search + context) — sending the query plus libraryName/libraryId is the docs-lookup function; calls fire on tool-call only, never on launch. No third-party telemetry SDK (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/context7.json. This page describes observed behaviour and its relation to the tool's own disclosures — it is not a legal judgment. Search context: does @upstash/context7-mcp send data, @upstash/context7-mcp privacy, @upstash/context7-mcp data flow, @upstash/context7-mcp telemetry, where does @upstash/context7-mcp send data, is @upstash/context7-mcp safe, what data does @upstash/context7-mcp collect, how to disable @upstash/context7-mcp telemetry, @upstash/context7-mcp opt out tracking, @upstash/context7-mcp GDPR data residency, @upstash/context7-mcp third-party / jurisdiction.