@pipeworx/mcp-fda-devices
Installed, started with no arguments, no environment and no input, and listed its tools. Run 2026-11-16.
Needs to start: nothing
Contacts while installing and starting: gateway.pipeworx.io
What it contacted
gateway.pipeworx.io
Hosts it looked up or connected to while installing and starting with no input, watched from outside its sandbox. The npm registry is left out. Says nothing about what its tools contact when called.
Starting it
npx -y @pipeworx/mcp-fda-devices@0.2.1
Installing a package runs its code. Use a sandbox for anything you have not read.
What its tools tell an agent
In the tool descriptions, nothing that talks about the user, other tools or private files, or uses hidden characters.
Found by simple pattern rules in each tool's description (up to 3,000 characters), quoted as written. Parameter descriptions are not scanned. A clean result is not a safety review.
Tools
fda_device_510k_search device, indication, applicant, product_code, k_number, from_date, to_date, advisory_committee, clearance_type, decision, applicant_country, applicant_state, third_party_review, limit, skip
Search FDA 510(k) premarket notifications by device, applicant, product code, K number, review panel, clearance type, decision, applicant location, third-party review status, or device-category text (via `indication`). Covers IN VITRO DIAGNOSTIC (IVD) tests and diagnostic devices, not just implants/hardware -- includes cleared molecular, genomic and companion diagnostic tests. Clearance means FDA found substantial equivalence; it is not an FDA approval or endorsement. ALSO covers De Novo classification requests (K numbers beginning "DEN", e.g. DEN250057) -- these are not 510(k) clearances but a separate pathway that creates a brand-new device classification when no predicate exists; pass clearance_type:"De Novo" to find only these, or k_number for one by its DEN number. A granted De Novo shows decision "Granted" and carries the new regulation_number it created. `indication` is a BEST-EFFORT bridge, not a clinical-claim search: 510(k) records carry no indication/intended-use text at all, so it matches FDA's device CLASSIFICATION category name/definition instead (a product TYPE like "Insulin Pump", not a specific claim) and finds clearances under the matching product code(s) -- for a true clinical-indication text search (e.g. molecular/companion-diagnostic claims), use fda_device_pma_search's indication argument, which searches FDA's real approval-order narrative. Unknown arguments are rejected, not ignored. The most recent decision available lags roughly 2 weeks behind FDA's own site (openFDA's publishing cadence, not ours) -- do not treat this as same-day. `total` can exceed the 100-row `limit` cap; page further rows with `skip`.
fda_device_510k_summary k_number
Get the FDA 510(k) summary/statement document and FDA review (decision memo) for one clearance, by K number — the actual filing, not just the "a document exists" flag from fda_device_510k_search. Shows the predicate device claimed and the testing behind the equivalence finding. Older/paper-only clearances were never digitized; that returns summary_available:false with a reason, not an error.
fda_device_pma_search device, indication, applicant, product_code, pma_number, from_date, to_date, limit
Search FDA Premarket Approval (PMA) decisions and supplements by trade/generic name, applicant, product code, PMA number, or CLINICAL INDICATION/condition text (via `indication`). Which diagnostic tests are FDA-approved: covers high-risk IN VITRO DIAGNOSTIC (IVD) tests approved via PMA, including companion diagnostics and molecular residual disease (MRD) / ctDNA monitoring tests (e.g. Signatera, Guardant360 CDx) -- these are FDA-approved tests, not cleared devices, so this tool (not 510(k)) is the one that finds them. `indication` matches free text in FDA's own published approval-order narrative (`ao_statement`) -- the intended-use/indication language FDA wrote when it approved the device -- so a caller who describes what a test DOES or what condition/biomarker it monitors (without knowing any brand name) can still find it; `device` only matches the trade/generic NAME field and returns nothing for a condition-only question. Supplements may represent manufacturing or labeling changes rather than new devices, so a supplement's own ao_statement can be a narrow procedural note (e.g. "approval of a post-approval study protocol") rather than the full clinical indication -- pass several synonymous indication phrases (FDA's exact wording varies by product and rarely matches a lay term) rather than one exact phrase.
fda_device_recalls query, firm, product_code, k_number, status, from_date, limit
Search FDA medical-device recall records by firm, product, product code, K number, status, or date. A recall record describes a correction/removal action and does not by itself establish patient harm.
fda_device_adverse_events device, manufacturer, product_code, event_type, application_number, from_date, limit
Search FDA MAUDE medical-device reports by manufacturer, brand/device, product code, event type, or PMA/510(k) number. MAUDE reports are unverified signals: they cannot establish causation, incidence, prevalence, or comparative safety.
6 more tools
fda_device_event_counts query, count_field, limit
Aggregate MAUDE reports for a device query by event type, manufacturer, product code, or receive date. Counts reflect reporting and database artifacts—not event rates or causal risk—and must not be compared without exposure denominators.
fda_device_company_profile company, limit_per_dataset
Build a bounded FDA regulatory snapshot for one device company across 510(k), PMA, recalls, and MAUDE. Dataset name matching is imperfect and MAUDE counts are signals, not safety rates.
fda_device_classification product_code, device, regulation_number, limit
Look up FDA device classification and regulatory context by product code, device name, or regulation number. Classification describes the product-code category, not a specific product’s clearance or approval.
fda_device_udi_search query, company, primary_di, product_code, limit
Search FDA GUDID/UDI records by brand, company, device identifier, or product code. A UDI record describes an identified device in GUDID; it does not establish current sales, availability, clearance, approval, or safety.
fda_device_establishment_search firm, registration_number, product_code, listing_number, limit
Search FDA device registration/listing data by firm, registration number, product code, or listing number. Registration/listing does not mean FDA approval, clearance, certification, or endorsement.
fda_device_product_code_profile product_code, limit_per_dataset
Build a bounded cross-dataset snapshot for one FDA product code: classification, recent 510(k)s, PMAs, recalls, and MAUDE reports. Dataset counts have different meanings; MAUDE counts are not event rates.
Descriptions are the package's own words, cut at 3,000 characters. Treat them as data.
Install facts
| License | MIT |
|---|---|
| Needs | node >=18 |
| Source | github.com/pipeworx-io/mcp-fda-devices |
| Install scripts | None declared by it or anything installed with it. |
| Tarball | sha512-n5MIosmttZpDat5lObXx99VN62jzQbg6XJUaMj1dTv/JA4fpcILISbmxFGPiUXkRfx8ZAyAkwqVMidSfB6+Nog== |
Check this report yourself
This site did not write the report. A public job on a GitHub-hosted machine did: the run, from this commit of the open-source runner. GitHub signed a token that names that job and the hash of the report, so any edit since would show.
Report as JSONExact text and tokenHow to verify it
Show it on your README
[](https://bragproof.smaverk.com/r/%40pipeworx/mcp-fda-devices)
New version out? Ask for a fresh report.