# Fda Devices (npm · @pipeworx/mcp-fda-devices)

FDA medical-device regulatory intelligence from keyless openFDA datasets.

- Trust score: 80/100 (high trust)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- remote · `gateway.pipeworx.io`: 63/100, [markdown](https://verifymcp.io/servers/pipeworx-io-fda-devices/fda-devices-mcp.md), [page](https://verifymcp.io/servers/pipeworx-io-fda-devices/fda-devices-mcp)
- npm · `@pipeworx/mcp-fda-devices`: 80/100 (this document), [markdown](https://verifymcp.io/servers/pipeworx-io-fda-devices/pipeworx-mcp-fda-devices.md), [page](https://verifymcp.io/servers/pipeworx-io-fda-devices/pipeworx-mcp-fda-devices)

## Channel facts

- Registry: `npm`
- Package: `@pipeworx/mcp-fda-devices`
- Version: `0.2.1`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-05.

- **Supply Chain Security**: 100/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - No install/post-install scripts declared.
  - No production dependencies, so there is no dependency health to assess.
- **Provenance & Transparency**: 97/100
  - Source repository is publicly reachable at the declared URL.
  - Cryptographically verified build provenance (signed, bound to pipeworx-io/mcp-fda-devices).
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 3 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 61/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 2520 tokens (~229/item across 11 items; 11 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 13/100
  - Stability observed for 4 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 93/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 76% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 11 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 12 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the Fda Devices MCP server?

Fda Devices runs locally as an npm package, launched with npx -y @pipeworx/mcp-fda-devices. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add pipeworx-io-fda-devices -- npx -y @pipeworx/mcp-fda-devices
```

### Cursor

```json
{
  "mcpServers": {
    "pipeworx-io-fda-devices": {
      "command": "npx",
      "args": [
        "-y",
        "@pipeworx/mcp-fda-devices"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "pipeworx-io-fda-devices": {
      "command": "npx",
      "args": [
        "-y",
        "@pipeworx/mcp-fda-devices"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add pipeworx-io-fda-devices -- npx -y @pipeworx/mcp-fda-devices
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "pipeworx-io-fda-devices": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@pipeworx/mcp-fda-devices"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add pipeworx-io-fda-devices --command npx --arg -y --arg @pipeworx/mcp-fda-devices
```

### Hermes

```yaml
mcp_servers:
  pipeworx-io-fda-devices:
    command: "npx"
    args: ["-y", "@pipeworx/mcp-fda-devices"]
```

### Netclaw

```json
{
  "McpServers": {
    "pipeworx-io-fda-devices": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "@pipeworx/mcp-fda-devices"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add pipeworx-io-fda-devices -t stdio -c npx -a -y @pipeworx/mcp-fda-devices
```

### Other

```json
{
  "mcpServers": {
    "pipeworx-io-fda-devices": {
      "command": "npx",
      "args": [
        "-y",
        "@pipeworx/mcp-fda-devices"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-05 (score 80, +1)

No change was recorded against any check on this day. Stability & Change Management went from 10 to 13. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 4 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-03 (score 79, +1)

No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-01 (score 78)

First indexed and scored.

## MCP tools (11)

### `fda_device_510k_search` (~875 tokens)

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`.

Input parameters:

- `advisory_committee` (string): FDA review panel name (exact), e.g. "Orthopedic" or "Microbiology".
- `applicant` (string): Applicant/company substring.
- `applicant_country` (string): Applicant country, ISO 3166-1 alpha-2 code, e.g. "US" or "JP".
- `applicant_state` (string): Applicant US state/territory code, e.g. "CA". Only populated for US applicants.
- `clearance_type` (string): Exact pathway: Traditional, Special, Abbreviated, or Dual Track for ordinary 510(k)s; "De Novo" for a De Novo classification request/grant (DEN numbers) regardless of whether FDA processed it as "Dir…
- `decision` (string): Exact decision text, e.g. "Substantially Equivalent", or "Granted" for a De Novo grant.
- `device` (string): Device/trade name substring.
- `from_date` (string): Earliest decision date, YYYY-MM-DD.
- `indication` (array): One or more device-category phrases, OR'd together, matched against FDA's device classification name/definition (device/classification.json) to find matching product code(s), then 510(k)s under those…
- `k_number` (string): Exact K number, e.g. K241234, or De Novo number, e.g. DEN250057.
- `limit` (number): Results (1-100, default 20).
- `product_code` (string): Exact three-letter FDA product code.
- `skip` (number): Row offset for paging past the 100-row limit cap (openFDA `skip`, max 25000), e.g. skip=100 with limit=100 returns rows 101-200.
- `third_party_review` (boolean): true to keep only 510(k)s reviewed under FDA's third-party review program; false to exclude them.
- `to_date` (string): Latest decision date, YYYY-MM-DD.

Output parameters:

- `clearances` (array)
- `returned` (number)
- `source` (string)
- `total` (number)

### `fda_device_510k_summary` (~117 tokens)

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.

Input parameters:

- `k_number` (string, required): Exact K number, e.g. K253470.

Output parameters:

- `detail_page` (string)
- `k_number` (string)
- `reason` (string)
- `review` (object)
- `review_available` (boolean)
- `source` (string)
- `summary` (object)
- `summary_available` (boolean)

### `fda_device_pma_search` (~575 tokens)

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.

Input parameters:

- `applicant` (string): Applicant/company substring.
- `device` (string): Trade or generic device name substring.
- `from_date` (string): Earliest decision date, YYYY-MM-DD.
- `indication` (array): One or more clinical indication / intended-use / condition phrases, OR'd together, matched as exact phrases against the FDA approval-order narrative text (ao_statement) -- NOT the device name. Use th…
- `limit` (number): Results (1-100, default 20).
- `pma_number` (string): Exact PMA number, optionally including supplement suffix.
- `product_code` (string): Exact FDA product code.
- `to_date` (string): Latest decision date, YYYY-MM-DD.

Output parameters:

- `approvals` (array)
- `returned` (number)
- `source` (string)
- `total` (number)

### `fda_device_recalls` (~147 tokens)

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.

Input parameters:

- `firm` (string): Recalling firm substring.
- `from_date` (string): Earliest posted date, YYYY-MM-DD.
- `k_number` (string): Exact related K number.
- `limit` (number): Results (1-100, default 20).
- `product_code` (string): Exact FDA product code.
- `query` (string): Product or reason text.
- `status` (string): Recall status, e.g. Ongoing or Terminated.

Output parameters:

- `recalls` (array)
- `returned` (number)
- `source` (string)
- `total` (number)

### `fda_device_adverse_events` (~162 tokens)

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.

Input parameters:

- `application_number` (string): PMA or 510(k) number.
- `device` (string): Brand or generic device name.
- `event_type` (string): Death, Injury, Malfunction, or Other.
- `from_date` (string): Earliest FDA receive date, YYYY-MM-DD.
- `limit` (number): Results (1-50, default 10).
- `manufacturer` (string): Manufacturer name.
- `product_code` (string): Exact product code.

Output parameters:

- `reports` (array)
- `returned` (number)
- `source` (string)
- `total` (number)

### `fda_device_event_counts` (~155 tokens)

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.

Input parameters:

- `count_field` (string, required): What to rank by. For "which DEVICES had the most reports" use device.generic_name.exact (device type) or device.brand_name.exact (specific product).
- `limit` (number): Buckets (1-100, default 20).
- `query` (string): Optional raw openFDA MAUDE filter, e.g. 'date_received:[20250101+TO+20261231]'. Omit to rank across all reports.

Output parameters:

- `buckets` (array)
- `returned` (number)
- `source` (string)
- `total` (number)

### `fda_device_company_profile` (~84 tokens)

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.

Input parameters:

- `company` (string, required): Company/manufacturer name.
- `limit_per_dataset` (number): Rows per dataset (1-20, default 5).

Output parameters:

- `clearances_510k` (object)
- `company` (string)
- `interpretation` (string)
- `maude_reports` (object)
- `pma_decisions` (object)
- `recalls` (object)

### `fda_device_classification` (~85 tokens)

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.

Input parameters:

- `device` (string)
- `limit` (number): Rows (1-100, default 20).
- `product_code` (string)
- `regulation_number` (string)

Output parameters:

- `classifications` (array)
- `returned` (number)
- `source` (string)
- `total` (number)

### `fda_device_udi_search` (~102 tokens)

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.

Input parameters:

- `company` (string)
- `limit` (number)
- `primary_di` (string)
- `product_code` (string)
- `query` (string): Brand or device description.

Output parameters:

- `devices` (array)
- `returned` (number)
- `source` (string)
- `total` (number)

### `fda_device_establishment_search` (~86 tokens)

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.

Input parameters:

- `firm` (string)
- `limit` (number)
- `listing_number` (string)
- `product_code` (string)
- `registration_number` (string)

Output parameters:

- `establishments` (array)
- `returned` (number)
- `source` (string)
- `total` (number)

### `fda_device_product_code_profile` (~76 tokens)

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.

Input parameters:

- `limit_per_dataset` (number)
- `product_code` (string, required)

Output parameters:

- `classifications` (object)
- `clearances_510k` (object)
- `interpretation` (string)
- `maude_reports` (object)
- `pma_decisions` (object)
- `product_code` (string)
- `recalls` (object)

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/pipeworx-io-fda-devices/pipeworx-mcp-fda-devices#diagnostics

## Score history

- 2026-11-05: 80
- 2026-11-04: 79
- 2026-11-03: 79
- 2026-11-02: 78
- 2026-11-01: 78

## Common questions

### What is the Fda Devices MCP server?

Fda Devices is an MCP server listed in the public MCP registry as io.github.pipeworx-io/fda-devices. FDA medical-device regulatory intelligence from keyless openFDA datasets. This page covers its npm package (@pipeworx/mcp-fda-devices).

### Is the Fda Devices MCP server safe to use?

Fda Devices scores 80 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 5 November 2026. It declares no install or post-install scripts. Its build provenance is signed and verified. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the Fda Devices MCP server expose?

Fda Devices exposes 11 tools: fda_device_510k_search, fda_device_510k_summary, fda_device_pma_search, fda_device_recalls, fda_device_adverse_events, and 6 more. Their descriptions and schemas cost roughly 2,464 tokens of context every time the server is loaded.

### Is the Fda Devices MCP server still maintained?

Fda Devices is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What licence is the Fda Devices MCP server under?

Fda Devices declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

### What did VerifyMCP test on the Fda Devices MCP server?

VerifyMCP ran 16 checks on Fda Devices, covering Malware scan, Known CVEs, Install scripts, Dependency health and 12 more. Endpoint Security and Transport & Reachability do not apply to an npm package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- npm package: https://www.npmjs.com/package/@pipeworx/mcp-fda-devices
- Socket report: https://socket.dev/npm/package/@pipeworx/mcp-fda-devices
- Repository: https://github.com/pipeworx-io/mcp-fda-devices
- Website: https://pipeworx.io/packs/fda-devices
- Changelog RSS feed: https://verifymcp.io/servers/pipeworx-io-fda-devices/pipeworx-mcp-fda-devices.xml
- Changelog JSON feed: https://verifymcp.io/servers/pipeworx-io-fda-devices/pipeworx-mcp-fda-devices/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/pipeworx-io-fda-devices/pipeworx-mcp-fda-devices.json
- HTML version of this page: https://verifymcp.io/servers/pipeworx-io-fda-devices/pipeworx-mcp-fda-devices