# Clinicaltables (npm · @pipeworx/mcp-clinicaltables)

NIH Clinical Tables Search Service MCP.

- Trust score: 77/100 (medium)
- Change this week: −2
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- remote · `gateway.pipeworx.io`: 84/100, [markdown](https://verifymcp.io/servers/pipeworx-io-clinicaltables/clinicaltables-mcp.md), [page](https://verifymcp.io/servers/pipeworx-io-clinicaltables/clinicaltables-mcp)
- npm · `@pipeworx/mcp-clinicaltables`: 77/100 (this document), [markdown](https://verifymcp.io/servers/pipeworx-io-clinicaltables/pipeworx-mcp-clinicaltables.md), [page](https://verifymcp.io/servers/pipeworx-io-clinicaltables/pipeworx-mcp-clinicaltables)

## Channel facts

- Registry: `npm`
- Package: `@pipeworx/mcp-clinicaltables`
- 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**: 71/100
  - Repository presence not verified: we could not reach the forge to check. This is a gap on our side, not a finding about the repository.
  - Cryptographically verified build provenance (signed, bound to pipeworx-io/mcp-clinicaltables).
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 5 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 62/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 2437 tokens (~243/item across 10 items; 10 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 23/100
  - Stability observed for 7 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 10 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 11 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 Clinicaltables MCP server?

Clinicaltables runs locally as an npm package, launched with npx -y @pipeworx/mcp-clinicaltables. 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-clinicaltables -- npx -y @pipeworx/mcp-clinicaltables
```

### Cursor

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

### VS Code

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

### Codex

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

### opencode

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

### OpenClaw

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

### Hermes

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

### Netclaw

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

### Vellum

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

### Other

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

## 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 77, −4)

- [security regression] Provenance: pass → unverified

### 2026-11-03 (score 81, +1)

No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-01 (score 80, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-10-31 (score 65, −14)

- [security regression] Malware scan: pass → unverified
- [functional] Package version: 0.2.0 → 0.2.1

### 2026-10-29 (score 79)

First indexed and scored.

## MCP tools (10)

### `conditions` (~223 tokens)

"What is [condition]" / "look up medical condition by name" / "find a disease called [X]" / "patient-friendly medical term for [Y]" — search the NLM patient-friendly medical conditions vocabulary (~700 common conditions written for lay readers). Returns canonical names like "Migraine", "Type 2 diabetes". Use for symptom-to-condition lookup, intake forms, or simplifying clinical text for patients.

Input parameters:

- `count` (number): Maximum matches to return. Default 7, max 500. Use 1–3 for typeahead UX, 20–50 for browsing.
- `df` (string): Comma-separated display fields to use in the `displays` array. Default varies per table; usually the canonical name.
- `ef` (string): Comma-separated extra fields to include per match. Field names vary per table; check NLM docs at clinicaltables.nlm.nih.gov.
- `terms` (string, required): Search query — prefix/contains match against canonical names. Whitespace-split into AND tokens. Example: "migraine".

### `icd10cm` (~238 tokens)

"What's the ICD-10 code for [diagnosis]" / "diagnosis code lookup" / "billing code for [condition]" / "EHR code for [X]" — search ICD-10-CM diagnostic codes (US clinical modification, ~96k codes). Returns code + full description. Use for medical billing, EHR diagnosis coding, claim coding. Example: terms="diab" → E11.9 Type 2 diabetes mellitus without complications.

Input parameters:

- `count` (number): Maximum matches to return. Default 7, max 500. Use 1–3 for typeahead UX, 20–50 for browsing.
- `df` (string): Comma-separated display fields to use in the `displays` array. Default varies per table; usually the canonical name.
- `ef` (string): Comma-separated extra fields to include per match. Field names vary per table; check NLM docs at clinicaltables.nlm.nih.gov.
- `terms` (string, required): Search query — prefix/contains match against canonical names. Whitespace-split into AND tokens. Example: "type 2 diabetes".

### `icd9cm` (~204 tokens)

"Old ICD-9 code for [diagnosis]" / "pre-2015 diagnosis codes" — search legacy ICD-9-CM diagnostic codes. Use ONLY when working with pre-2015 US clinical records; new claims must use icd10cm. Same shape as icd10cm.

Input parameters:

- `count` (number): Maximum matches to return. Default 7, max 500. Use 1–3 for typeahead UX, 20–50 for browsing.
- `df` (string): Comma-separated display fields to use in the `displays` array. Default varies per table; usually the canonical name.
- `ef` (string): Comma-separated extra fields to include per match. Field names vary per table; check NLM docs at clinicaltables.nlm.nih.gov.
- `terms` (string, required): Search query — prefix/contains match against canonical names. Whitespace-split into AND tokens. Example: "asthma".

### `procedures` (~272 tokens)

"What is the procedure called [X]" / "medical procedure name lookup" / "patient-friendly name for [surgery]" — search clinical procedure names (NLM curated, ~7k entries). Returns short names like "Appendectomy", "Knee replacement". Patient-facing language; use for forms or intake screens. This vocabulary is SMALL and curated, so common terms can legitimately miss ("colonoscopy" and "MRI" both return 0, verified 2026-09-16) — a no_match here means "not in this list", not "no such procedure". For billing codes use icd10cm or a CPT source instead.

Input parameters:

- `count` (number): Maximum matches to return. Default 7, max 500. Use 1–3 for typeahead UX, 20–50 for browsing.
- `df` (string): Comma-separated display fields to use in the `displays` array. Default varies per table; usually the canonical name.
- `ef` (string): Comma-separated extra fields to include per match. Field names vary per table; check NLM docs at clinicaltables.nlm.nih.gov.
- `terms` (string, required): Search query — prefix/contains match against canonical names. Whitespace-split into AND tokens. Example: "appendectomy".

### `drugs` (~289 tokens)

"Drug name lookup" / "find prescription [X]" / "medication autocomplete" / "RxCUI for [drug]" / "what does [pill] treat" / "available strengths for [drug]" — search RxTerms (NLM prescribing-vocabulary derived from RxNorm, ~22k drug names with route/strength). Returns names like "Aspirin (Chewable)", "Lisinopril (Oral Pill)". Use for prescription entry, drug name autocomplete, or as a stepping-stone to RxNorm RxCUI lookups. Pass ef="STRENGTHS_AND_FORMS,RXCUIS" to include dosage strengths and RxNorm IDs.

Input parameters:

- `count` (number): Maximum matches to return. Default 7, max 500. Use 1–3 for typeahead UX, 20–50 for browsing.
- `df` (string): Comma-separated display fields to use in the `displays` array. Default varies per table; usually the canonical name.
- `ef` (string): Comma-separated extra fields to include per match. Known fields: STRENGTHS_AND_FORMS,RXCUIS,DISPLAY_NAME_SYNONYM,IS_RETIRED.
- `terms` (string, required): Search query — prefix/contains match against canonical names. Whitespace-split into AND tokens. Example: "aspirin".

### `loinc` (~225 tokens)

"LOINC code for [lab test]" / "standard code for blood test [X]" / "lab result identifier lookup" / "normalize lab name [Y]" — search LOINC lab test codes (Logical Observation Identifiers Names and Codes, universal lab test identifiers). Returns codes like "2093-3 Cholesterol [Mass/Vol] Ser/Plas". Use when normalizing lab results across institutions.

Input parameters:

- `count` (number): Maximum matches to return. Default 7, max 500. Use 1–3 for typeahead UX, 20–50 for browsing.
- `df` (string): Comma-separated display fields to use in the `displays` array. Default varies per table; usually the canonical name.
- `ef` (string): Comma-separated extra fields to include per match. Field names vary per table; check NLM docs at clinicaltables.nlm.nih.gov.
- `terms` (string, required): Search query — prefix/contains match against canonical names. Whitespace-split into AND tokens. Example: "cholesterol".

### `npi_individual` (~236 tokens)

"Find a doctor / clinician / physician by name" / "look up NPI for [provider]" / "verify a doctor's credentials" / "what's [Dr. X]'s NPI" — search the NPPES National Provider Identifier registry for individual US healthcare providers (~5M entries). Returns NPI numbers + provider names. terms can be a name fragment, NPI, or specialty. Use ef to include address, specialty, gender.

Input parameters:

- `count` (number): Maximum matches to return. Default 7, max 500. Use 1–3 for typeahead UX, 20–50 for browsing.
- `df` (string): Comma-separated display fields to use in the `displays` array. Default varies per table; usually the canonical name.
- `ef` (string): Comma-separated extra fields to include per match. Known fields: name.first,name.last,addr_practice.full,licenses.taxonomy.classification.
- `terms` (string, required): Search query — prefix/contains match against canonical names. Whitespace-split into AND tokens. Example: "smith pediatrics".

### `npi_organization` (~228 tokens)

"Find a hospital / clinic by name" / "look up NPI for [organization]" / "what's [Mayo Clinic]'s NPI" / "verify a healthcare facility" — search the NPPES NPI registry for organizational providers (~1.8M entries) — hospitals, clinics, group practices. Same shape as npi_individual. terms can be org name, NPI, or city.

Input parameters:

- `count` (number): Maximum matches to return. Default 7, max 500. Use 1–3 for typeahead UX, 20–50 for browsing.
- `df` (string): Comma-separated display fields to use in the `displays` array. Default varies per table; usually the canonical name.
- `ef` (string): Comma-separated extra fields to include per match. Known fields: name.full,addr_practice.full,licenses.taxonomy.classification.
- `terms` (string, required): Search query — prefix/contains match against canonical names. Whitespace-split into AND tokens. Example: "mayo clinic".

### `ucum` (~223 tokens)

"Unit of measure code for [X]" / "standard UCUM unit for [Y]" / "mg/dL code" — search UCUM (the Unified Code for Units of Measure, used by FHIR, LOINC, and most modern health-IT systems). Returns codes like "mg/dL", "[in_i]" (inch). Use when normalizing lab result units or rendering measurements.

Input parameters:

- `count` (number): Maximum matches to return. Default 7, max 500. Use 1–3 for typeahead UX, 20–50 for browsing.
- `df` (string): Comma-separated display fields to use in the `displays` array. Default varies per table; usually the canonical name.
- `ef` (string): Comma-separated extra fields to include per match. Field names vary per table; check NLM docs at clinicaltables.nlm.nih.gov.
- `terms` (string, required): Search query — prefix/contains match against canonical names. Whitespace-split into AND tokens. Example: "mg/dL".

### `disease_names` (~245 tokens)

"UMLS code for [disease]" / "clinical name for rare disease [X]" / "look up a syndrome by name" / "find CUI for [condition]" — search the NLM Disease Names vocabulary (UMLS-derived, broader than `conditions`; includes rare diseases, syndromes, clinical terminology, ~12k entries). Returns UMLS CUIs (e.g., C0011860) plus canonical names. Use when you need clinical-grade vocabulary linkage rather than patient-friendly labels.

Input parameters:

- `count` (number): Maximum matches to return. Default 7, max 500. Use 1–3 for typeahead UX, 20–50 for browsing.
- `df` (string): Comma-separated display fields to use in the `displays` array. Default varies per table; usually the canonical name.
- `ef` (string): Comma-separated extra fields to include per match. Field names vary per table; check NLM docs at clinicaltables.nlm.nih.gov.
- `terms` (string, required): Search query — prefix/contains match against canonical names. Whitespace-split into AND tokens. Example: "amyotrophic lateral sclerosis".

## Diagnostics

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

## Score history

- 2026-11-05: 77
- 2026-11-04: 81
- 2026-11-03: 81
- 2026-11-02: 80
- 2026-11-01: 80
- 2026-10-31: 65
- 2026-10-30: 79
- 2026-10-29: 79

## Common questions

### What is the Clinicaltables MCP server?

Clinicaltables is an MCP server listed in the public MCP registry as io.github.pipeworx-io/clinicaltables. NIH Clinical Tables Search Service MCP. This page covers its npm package (@pipeworx/mcp-clinicaltables).

### Is the Clinicaltables MCP server safe to use?

Clinicaltables scores 77 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 Clinicaltables MCP server expose?

Clinicaltables exposes 10 tools: conditions, icd10cm, icd9cm, procedures, drugs, and 5 more. Their descriptions and schemas cost roughly 2,383 tokens of context every time the server is loaded.

### Is the Clinicaltables MCP server still maintained?

Clinicaltables 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 Clinicaltables MCP server under?

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

## Links

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