# io.github.cyanheads/pharmacogenomics-guidelines-mcp-server (remote · pharmacogenomics-guidelines.caseyjhand.com)

Find pharmacogenomics guidelines, translate diplotypes, and retrieve prescribing recommendations.

- Trust score: 80/100 (high trust)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- remote · `pharmacogenomics-guidelines.caseyjhand.com`: 80/100 (this document), [markdown](https://verifymcp.io/servers/cyanheads-pharmacogenomics-guidelines-mcp-server/pharmacogenomics-guidelines.md), [page](https://verifymcp.io/servers/cyanheads-pharmacogenomics-guidelines-mcp-server/pharmacogenomics-guidelines)
- npm · `@cyanheads/pharmacogenomics-guidelines-mcp-server`: 39/100, [markdown](https://verifymcp.io/servers/cyanheads-pharmacogenomics-guidelines-mcp-server/cyanheads-pharmacogenomics-guidelines-mcp-server.md), [page](https://verifymcp.io/servers/cyanheads-pharmacogenomics-guidelines-mcp-server/cyanheads-pharmacogenomics-guidelines-mcp-server)

## Channel facts

- Endpoint: `https://pharmacogenomics-guidelines.caseyjhand.com/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.3.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, 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.

- **Endpoint Security**: 83/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC is configured correctly; the domain's records validate against the full chain to the root.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 73/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 2233 tokens (~319/item across 7 items; 6 tools + 1 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 40/100
  - Stability observed for 12 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.
  - 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 6 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 8 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

## Install

### How do I install the io.github.cyanheads/pharmacogenomics-guidelines-mcp-server server?

io.github.cyanheads/pharmacogenomics-guidelines-mcp-server is a hosted endpoint at https://pharmacogenomics-guidelines.caseyjhand.com/mcp, so there is nothing to install locally. 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 --transport http cyanheads-pharmacogenomics-guidelines-mcp-server 'https://pharmacogenomics-guidelines.caseyjhand.com/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "cyanheads-pharmacogenomics-guidelines-mcp-server": {
      "url": "https://pharmacogenomics-guidelines.caseyjhand.com/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "cyanheads-pharmacogenomics-guidelines-mcp-server": {
      "type": "http",
      "url": "https://pharmacogenomics-guidelines.caseyjhand.com/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.cyanheads-pharmacogenomics-guidelines-mcp-server]
url = "https://pharmacogenomics-guidelines.caseyjhand.com/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "cyanheads-pharmacogenomics-guidelines-mcp-server": {
      "type": "remote",
      "url": "https://pharmacogenomics-guidelines.caseyjhand.com/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add cyanheads-pharmacogenomics-guidelines-mcp-server --url 'https://pharmacogenomics-guidelines.caseyjhand.com/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  cyanheads-pharmacogenomics-guidelines-mcp-server:
    url: "https://pharmacogenomics-guidelines.caseyjhand.com/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "cyanheads-pharmacogenomics-guidelines-mcp-server": {
      "Transport": "http",
      "Url": "https://pharmacogenomics-guidelines.caseyjhand.com/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add cyanheads-pharmacogenomics-guidelines-mcp-server -t streamable-http -u 'https://pharmacogenomics-guidelines.caseyjhand.com/mcp'
```

### Other

```json
{
  "mcpServers": {
    "cyanheads-pharmacogenomics-guidelines-mcp-server": {
      "type": "http",
      "url": "https://pharmacogenomics-guidelines.caseyjhand.com/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## 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.

### 2026-11-04 (score 80, +1)

No change was recorded against any check on this day. Stability & Change Management went from 33 to 37. That category is still filling its 30-day observation window: 10 days of observed history at the previous scan, 11 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-02 (score 79, +1)

No change was recorded against any check on this day. Stability & Change Management went from 27 to 30. That category is still filling its 30-day observation window: 8 days of observed history at the previous scan, 9 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-31 (score 78, +1)

No change was recorded against any check on this day. Stability & Change Management went from 20 to 23. That category is still filling its 30-day observation window: 6 days of observed history at the previous scan, 7 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-29 (score 77, +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.

### 2026-10-28 (score 76, +3)

- [functional improvement] Schema quality: 357 → 319
- [functional] First check of Schema quality: 100
- [functional] New resource “pharmacogenomics-guidelines-guide”
- [functional] Server version: 0.2.1 → 0.3.0

### 2026-10-27 (score 73, +1)

No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-25 (score 72, +1)

- [functional improvement] Stability: unverified → 0.03

### 2026-10-24 (score 71)

First indexed and scored.

## MCP tools (6)

### `pgx_search_pairs` (~367 tokens)

Search evaluated gene–drug pairs

Search evaluated gene–drug pairs by gene, literal drug-name substring, exact drug/RxNorm/ATC identifiers, evaluation level or testing label. Filters combine with AND; identifiers never fall back to name-only search. Results include source drug identifiers and guideline links for pgx_get_guideline. A pair evaluation is not a prescribing recommendation. Follow nextOffset to continue.

Input parameters:

- `atcId` (string): Exact ATC code (1–7 letters/digits) in any casing, optionally prefixed ATC: in any casing; outer whitespace is ignored and blank means unset.
- `cpicLevel` (string): Exact source CPIC evaluation level, not a prescribing recommendation.
- `drugId` (string): Exact drugId returned by pgx_search_pairs; blank means unset.
- `drugName` (string): Literal case-insensitive drug-name substring; blank means unset.
- `geneSymbol` (string): Exact gene symbol, case-insensitive input; blank means unset.
- `includeRetired` (boolean): Include Retired pairs; also included when cpicLevel is Retired.
- `limit` (integer): Positive safe-integer row limit; values above 100 are clamped to 100 with a notice (default 25).
- `offset` (integer): Zero-based offset; use nextOffset to continue (default 0).
- `pgxTesting` (string): ClinPGx label-annotation testing level; not an FDA label.
- `provisional` (boolean): Filter by source provisional flag.
- `rxnormId` (string): Decimal RxNorm ID, optionally prefixed RxNorm: in any casing; outer whitespace is ignored and blank means unset.
- `usedForRecommendation` (string): Whether the source marks the pair as used for a recommendation.

Output parameters:

- `cap` (integer): Effective public page limit.
- `effectiveQuery` (object): Normalized filters and effective paging.
- `error` (object): Present when the call failed. Absent on success.
- `items` (array): Complete evaluated pairs and related drugs.
- `notices` (array): Notices about this result; empty when none apply.
- `page` (object): Source pagination metadata.
- `provenance` (object): Live source attribution and retrieval details.
- `shown` (integer): Number of returned rows, equal to page.returned.
- `truncated` (boolean): Whether more matching rows remain after this page.

### `pgx_get_guideline` (~319 tokens)

Get guideline coverage

Retrieve guideline coverage by source ID, exact gene symbol or exact drug name/ID. Default summary pages complete guideline records with exact drugCount/pairCount. view=drugs or pairs requires by=id and pages only that related collection, retaining its guideline descriptor. Ambiguous drug names page candidates for retry with drugId. Follow page.nextOffset; the 24,000-byte soft budget cuts only between complete rows, with oversizedRow for an indivisible exception. Missing coverage is found=false. Consult linked guidelines before clinical use.

Input parameters:

- `by` (string, required): id requires guidelineId; gene requires geneSymbol; drug requires exactly one exact drugName or drugId. Other selectors must be omitted.
- `drugId` (string): Exact drugId returned by pgx_search_pairs; blank means unset.
- `drugName` (string): Exact case-insensitive source drug name for by=drug; blank means unset.
- `geneSymbol` (string): Gene symbol for by=gene; blank means unset.
- `guidelineId` (integer): Positive source guideline ID from pgx_get_guideline by=gene or by=drug results; no valid ID range is inferred.
- `limit` (integer): Positive safe-integer row limit; values above 100 are clamped to 100 with a notice (default 25).
- `offset` (integer): Zero-based offset; use nextOffset to continue (default 0).
- `view` (string): Summary pages guideline descriptors; drugs or pairs requires by=id and pages only that related collection.

Output parameters:

- `candidates` (array): Paged exact drug-name candidates when resolution is ambiguous; page and shown then refer to candidates.
- `cap` (integer): Effective public page limit.
- `clinicalCaveat` (string): Clinical qualification for source guidance.
- `drugs` (array): Selected drugs page; omitted in other views.
- `effectiveQuery` (object): Normalized guideline selectors and effective page bounds.
- `error` (object): Present when the call failed. Absent on success.
- `found` (boolean): Whether guideline coverage was found.
- `guidance` (string): Next lookup step when missing or ambiguous; empty when found.
- `guidelines` (array): Paged complete guideline descriptors, or the retained descriptor for a related view.
- `notices` (array): Notices about this result; empty when none apply.
- `oversizedRow` (boolean): Whether one complete indivisible row exceeds the soft byte budget.
- `page` (object): Source pagination metadata.
- `pairs` (array): Selected pairs page; omitted in other views.
- `provenance` (object): Live source attribution and retrieval details.
- `shown` (integer): Number of returned rows, equal to page.returned.
- `truncated` (boolean): Whether more matching rows remain after this page.
- `view` (string): Selected guideline view.

### `pgx_lookup_diplotype` (~157 tokens)

Look up diplotype

Translate a CPIC-supported diplotype or allele-status result for one gene. Supply geneSymbol and exact diplotype notation, including star alleles, named HLA positive/negative statuses, or non-star sequences; use pgx_search_alleles and pgx_list_reference with topic phenotypes to inspect supported values. Exact lookup precedes bounded reverse-order or status aliases. Multiple source rows remain ambiguous; no activity score or missing gene result is inferred.

Input parameters:

- `diplotype` (string, required): Exact source diplotype or allele-specific status, such as *1/*2 or *15:02 positive.
- `geneSymbol` (string, required): Gene symbol, such as CYP2C19 or HLA-B; outer whitespace is ignored.

Output parameters:

- `effectiveQuery` (object): Effective diplotype query.
- `error` (object): Present when the call failed. Absent on success.
- `found` (boolean): Whether at least one source row matched.
- `geneSymbol` (string): Normalized supplied gene symbol.
- `guidance` (string): Recovery guidance for missing or ambiguous source rows.
- `inputDiplotype` (string): Trimmed caller notation.
- `matchedDiplotype` (string|null): Notation matched in the source, or null.
- `notices` (array): Notices about this result; empty when none apply.
- `provenance` (object): Live source attribution and retrieval details.
- `records` (array): Every matching source row; multiple rows are ambiguous.

### `pgx_get_recommendations` (~542 tokens)

Get recommendations

Browse CPIC recommendations in drug mode with one exact drugName or drugId. Match across drugs in results mode with geneResults or geneSymbol plus phenotype/activityScore, or genotype mode with 1–10 uniquely resolved gene/diplotype entries. Both matching modes accept an optional drug. Optional view=test_alerts selects complete example CDS alerts instead of recommendations, without joins; default view=recommendations. Alert records retain ordered alerttext, No CDS and n/a. Use pgx_list_reference topic phenotypes for source values. Every matched prerequisite must be explicit; omitted genes are never normal, negative or No Result. Preserve populations, scores, classifications and source text. Follow page.nextOffset and incompletePage.nextOffset independently for the selected collection and missing-gene diagnostics; consult source guidelines before clinical use.

Input parameters:

- `activityScore`: Source activity score for geneSymbol; excludes phenotype and geneResults.
- `drugId` (string): Exact drugId returned by pgx_search_pairs; blank means unset.
- `drugName` (string): Exact case-insensitive drug name; obtain names with pgx_search_pairs. Blank means unset.
- `geneResults` (object): Explicit results for 1–10 genes; excludes scalar geneSymbol, phenotype, activityScore and genotype.
- `geneSymbol` (string): Gene for a scalar result or exploratory gene filter. Required for a scalar result when the drug has multiple genes.
- `genotype` (object): Required in genotype mode: 1–10 explicit gene/diplotype entries. Every entry must resolve uniquely before lookup.
- `incompleteLimit` (integer): Positive safe-integer incomplete diagnostic limit; values above 100 are clamped to 100 with a notice (default 25).
- `incompleteOffset` (integer): Independent zero-based incomplete diagnostic offset; follow incompletePage.nextOffset.
- `limit` (integer): Positive safe-integer recommendation limit; values above 50 are clamped to 50 with a notice (default 10).
- `mode` (string, required): drug requires one drugName or drugId; genotype requires genotype; results requires geneResults or geneSymbol with phenotype/activityScore. Genotype/results optionally accept one drug selector.
- `offset` (integer): Zero-based offset; use nextOffset to continue (default 0).
- `phenotype` (string): Source phenotype for geneSymbol; inspect pgx_list_reference topic phenotypes. Excludes activityScore and geneResults.
- `population` (string): Exact source population after outer whitespace trimming; all matching rows are retained.
- `view` (string): Select source recommendations (default) or example CDS test alerts with the same selectors and independent paging.

Output parameters:

- `alerts` (array): Complete source alerts in test_alerts view only; recommendation items remain empty.
- `cap` (integer): Effective public page limit.
- `clinicalCaveat` (string): Source limitations and required clinical qualification.
- `effectiveQuery` (object): Normalized selectors and effective page defaults.
- `error` (object): Present when the call failed. Absent on success.
- `geneResolutions` (array): Per-gene genotype diagnostics, including ambiguity and source records.
- `incompleteAlerts` (array): Independently paged incomplete alerts in test_alerts view only.
- `incompleteMatches` (array): Reference possibilities requiring additional results; never matched prescribing advice.
- `incompletePage` (object): Independent page of incomplete prerequisite diagnostics; totals computed before either page.
- `items` (array): Complete source records; matched rows have every required gene result explicitly supplied.
- `notices` (array): Notices about this result; empty when none apply.
- `page` (object): Source pagination metadata.
- `provenance` (object): Live source attribution and retrieval details.
- `shown` (integer): Number of returned rows, equal to page.returned.
- `status` (string): Exploratory browsing, complete genetic match, no match, missing prerequisites, or unresolved genotype.
- `truncated` (boolean): Whether more matching rows remain after this page.

### `pgx_search_alleles` (~234 tokens)

Search alleles

Inspect CPIC allele function, evidence, definition metadata and complete population frequencies for geneSymbol. Name matches literally first, then a matching gene prefix before a star allele may be removed; clinicalFunctionalStatus matches literal text case-insensitively. Discover genes with pgx_list_reference. Definitions are metadata, not variant interpretation. Frequencies are source fractions; inferred frequencies are not observations and do not establish individual risk. Pages have a 24,000-byte complete-result soft budget; an indivisible exception sets oversizedRow. Continue with page.nextOffset.

Input parameters:

- `clinicalFunctionalStatus` (string): Case-insensitive literal source clinical functional status; blank means unset.
- `geneSymbol` (string, required): Gene symbol, such as CYP2C19 or HLA-B; outer whitespace is ignored.
- `limit` (integer): Positive safe-integer row limit; values above 100 are clamped to 100 with a notice (default 25).
- `name` (string): Exact source allele name; blank means unset.
- `offset` (integer): Zero-based offset; use nextOffset to continue (default 0).

Output parameters:

- `cap` (integer): Effective public page limit.
- `effectiveQuery` (object): Effective allele selectors and page bounds.
- `error` (object): Present when the call failed. Absent on success.
- `items` (array): Source alleles, embedded definitions and population frequencies.
- `notices` (array): Notices about this result; empty when none apply.
- `oversizedRow` (boolean): Whether one complete indivisible row exceeds the soft byte budget.
- `page` (object): Source pagination metadata.
- `provenance` (object): Live source attribution and retrieval details.
- `shown` (integer): Number of returned rows, equal to page.returned.
- `truncated` (boolean): Whether more matching rows remain after this page.

### `pgx_list_reference` (~190 tokens)

List pharmacogenomics reference values

Inspect gene symbols, gene-specific source results, CPIC levels, ClinPGx testing labels, recommendation classifications and input formats. phenotypes requires geneSymbol and preserves distinct activity-score rows, frequencies and consultation text. Live genes/phenotypes support paging; static topics return their complete vocabulary without upstream requests. Use returned values in subsequent discovery, diplotype and recommendation calls.

Input parameters:

- `geneSymbol` (string): Exact gene symbol; required for phenotypes, optional for genes, omit for static topics.
- `limit` (integer): Positive safe-integer row limit; values above 100 are clamped to 100 with a notice (default 25).
- `offset` (integer): Zero-based offset; use nextOffset to continue (default 0).
- `topic` (string, required): genes lists source gene records; phenotypes requires geneSymbol and lists full gene-result rows; other topics return verified static vocabulary.

Output parameters:

- `cap` (integer): Effective public page limit.
- `effectiveQuery` (object): Normalized topic, gene selector and effective paging.
- `error` (object): Present when the call failed. Absent on success.
- `items` (array): Full live gene/result rows or complete static vocabulary entries.
- `notices` (array): Notices about this result; empty when none apply.
- `page` (object): Source pagination metadata.
- `provenance`: Live access provenance or static verification provenance.
- `shown` (integer): Number of returned rows, equal to page.returned.
- `truncated` (boolean): Whether more matching rows remain after this page.

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/cyanheads-pharmacogenomics-guidelines-mcp-server/pharmacogenomics-guidelines#diagnostics

## Score history

- 2026-11-05: 80
- 2026-11-04: 80
- 2026-11-03: 79
- 2026-11-02: 79
- 2026-11-01: 78
- 2026-10-31: 78
- 2026-10-30: 77
- 2026-10-29: 77
- 2026-10-28: 76
- 2026-10-27: 73
- 2026-10-26: 72
- 2026-10-25: 72
- 2026-10-24: 71

## Common questions

### What is the io.github.cyanheads/pharmacogenomics-guidelines-mcp-server server?

io.github.cyanheads/pharmacogenomics-guidelines-mcp-server is listed in the public MCP registry as io.github.cyanheads/pharmacogenomics-guidelines-mcp-server. Find pharmacogenomics guidelines, translate diplotypes, and retrieve prescribing recommendations. This page covers its hosted endpoint (https://pharmacogenomics-guidelines.caseyjhand.com/mcp).

### Is the io.github.cyanheads/pharmacogenomics-guidelines-mcp-server server safe to use?

io.github.cyanheads/pharmacogenomics-guidelines-mcp-server scores 80 out of 100 on VerifyMCP. 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 io.github.cyanheads/pharmacogenomics-guidelines-mcp-server server expose?

io.github.cyanheads/pharmacogenomics-guidelines-mcp-server exposes 6 tools: pgx_search_pairs, pgx_get_guideline, pgx_lookup_diplotype, pgx_get_recommendations, pgx_search_alleles, pgx_list_reference. Their descriptions and schemas cost roughly 1,809 tokens of context every time the server is loaded.

### Does the io.github.cyanheads/pharmacogenomics-guidelines-mcp-server server require authentication?

No. We connected to io.github.cyanheads/pharmacogenomics-guidelines-mcp-server without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the io.github.cyanheads/pharmacogenomics-guidelines-mcp-server server still maintained?

io.github.cyanheads/pharmacogenomics-guidelines-mcp-server 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.

## Links

- Remote endpoint: https://pharmacogenomics-guidelines.caseyjhand.com/mcp
- Repository: https://github.com/cyanheads/pharmacogenomics-guidelines-mcp-server
- Changelog RSS feed: https://verifymcp.io/servers/cyanheads-pharmacogenomics-guidelines-mcp-server/pharmacogenomics-guidelines.xml
- Changelog JSON feed: https://verifymcp.io/servers/cyanheads-pharmacogenomics-guidelines-mcp-server/pharmacogenomics-guidelines.json
- HTML version of this page: https://verifymcp.io/servers/cyanheads-pharmacogenomics-guidelines-mcp-server/pharmacogenomics-guidelines