# DeepDNA

> Pharmacogenomics for AI agents: cited drug–gene, gene and rsID lookups plus a medication screen.

- name: ai.deepdna/knowledge
- version: 1.2.0
- connection class: R0 (autonomous)
- trust: 82/100 flags: no-repository
- quality: 85/100 (good)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/ai.deepdna%2Fknowledge
- tools: https://api.protogrid.dev/v1/servers/ai.deepdna%2Fknowledge/tools

**An agent can connect right now, no human step.** Remote endpoint, no authentication, reachable on the last probe.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "knowledge": {
      "type": "http",
      "url": "https://deepdna.ai/mcp"
    }
  }
}
```


## Trust

- hygiene: 80
- liveness: 98
- freshness: 100
- provenance: 55
- drivers: +dns-namespace +website +reachable +uptime-96% +updated-3d-ago -no-repository
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 85/100 (good)

### protocol: 88 (weight 25)

- pass `protocol.modern`: supports 2026-07-28 (server/discover)
- pass `protocol.stateless`: answers without a session
- pass `protocol.transport`: streamable HTTP
- warn `protocol.list_ttl`: tools/list carries no ttlMs, so clients re-fetch it

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 100 (weight 30)

- pass `tools.descriptions`: every tool has a description
- pass `tools.description_length`: descriptions are concise
- pass `tools.schemas`: every tool has an object input schema
- pass `tools.annotations`: 6 of 6 tools declare readOnlyHint or destructiveHint
- pass `tools.directory_hints`: every tool declares readOnlyHint, destructiveHint, idempotentHint and openWorldHint
- pass `tools.token_cost`: about 921 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: 50 (weight 15)

- pass `stability.changes`: 5 tool changes in 30 days
- fail `stability.rug_pull`: 2 tools kept their name but changed most of their description in 30 days; review before trusting them

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package

- tools: 6, about 921 tokens to load them all
- tool set hash: 8fa3702956b71c835f0c665040c52bf9
- tools last changed: 2026-10-17T16:44:50.725Z
- badge: [![protogrid quality](https://protogrid.dev/badge/ai.deepdna/knowledge.svg)](https://protogrid.dev/servers/ai.deepdna/knowledge)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

- 2026-10-17 `lookup_variant` changed (description, inputSchema) **meaning changed**
  - before: One variant by dbSNP rsID: gene, star-allele or common name, alleles, functional effect, population frequency and sources. Optionally pass the genotype read at that position (e.g. from a raw DNA file) to get how many copies of the variant allele it holds. That count is not a phenotype, metabolizer or risk call.
  - after: One variant by dbSNP rsID: gene, star-allele or common name, alleles, functional effect, population frequency and sources. Send the rsID only, never the user's genotype. To compare a raw DNA file, do it in the agent with the record's reading block (GRCh37 plus-strand reference and variant allele): skip it when countable is false, don't trust A/T or C/G positions (strand_ambiguous) unless the file's strand is known, and treat a chip call of a rare pathogenic variant as unconfirmed. A count at one position is not a phenotype or metabolizer status.
- 2026-10-11 `request_beta_access` added
  - Register the user's interest in DeepDNA's private beta (DNA file parsing, annotation, bloodwork; not deployed yet). Only call this after the user has explicitly agreed to share their email with DeepDNA for this purpose, and set user_consent to true. Stores the email and the optional use case; see https://deepdna.ai/privacy/.
- 2026-10-11 `check_medications` added
  - Given a list of generic drug names, say which ones have a curated drug–gene record, with which genes and what each record rests on (a CPIC or DPWG guideline, a drug label, or the primary literature), and which are not covered. Needs no genotype. Use it before discussing whether genetics could matter for someone's medicines.
- 2026-10-11 `lookup_drug_gene` changed (description)
  - before: Pharmacogenomic guidance for a gene, optionally for one drug: guideline (CPIC/DPWG), summary of the recommendation, phenotypes and sources. Omit drug to list every drug curated for that gene.
  - after: Pharmacogenomic guidance for a gene, optionally for one drug: guideline (CPIC or DPWG, "drug label", or null when the record rests on the primary literature), summary of the recommendation, phenotypes and sources. Omit drug to list every drug curated for that gene.
- 2026-10-11 `lookup_variant` changed (description, inputSchema) **meaning changed**
  - before: One variant by dbSNP rsID: gene, star-allele or common name, alleles, functional effect, population frequency and sources.
  - after: One variant by dbSNP rsID: gene, star-allele or common name, alleles, functional effect, population frequency and sources. Optionally pass the genotype read at that position (e.g. from a raw DNA file) to get how many copies of the variant allele it holds. That count is not a phenotype, metabolizer or risk call.

Full history: https://api.protogrid.dev/v1/servers/ai.deepdna%2Fknowledge/changes

## Remotes

- https://deepdna.ai/mcp (streamable-http, auth none, reachable true, uptime30d 0.95652175)

## Packages

_none_

## Tools (6)

- `check_medications`: Given a list of generic drug names, say which ones have a curated drug–gene record, with which genes and what each record rests on (a CPIC or DPWG guideline, a drug label, or the primary literature), and which are not covered. Needs no genotype. Use it before discussing whether genetics could matter for someone's medicines.
- `list_genes`: List the genes in the DeepDNA knowledge base, with a one-line summary and category for each.
- `lookup_drug_gene`: Pharmacogenomic guidance for a gene, optionally for one drug: guideline (CPIC or DPWG, "drug label", or null when the record rests on the primary literature), summary of the recommendation, phenotypes and sources. Omit drug to list every drug curated for that gene.
- `lookup_gene`: Everything curated about one gene: function, key variants with rsIDs, metabolizer or function phenotypes, drug interactions, what a consumer genotyping array can and cannot tell you, and sources.
- `lookup_variant`: One variant by dbSNP rsID: gene, star-allele or common name, alleles, functional effect, population frequency and sources. Send the rsID only, never the user's genotype. To compare a raw DNA file, do it in the agent with the record's reading block (GRCh37 plus-strand reference and variant allele): skip it when countable is false, don't trust A/T or C/G positions (strand_ambiguous) unless the file's strand is known, and treat a chip call of a rare pathogenic variant as unconfirmed. A count at one position is not a phenotype or metabolizer status.
- `request_beta_access`: Register the user's interest in DeepDNA's private beta (DNA file parsing, annotation, bloodwork; not deployed yet). Only call this after the user has explicitly agreed to share their email with DeepDNA for this purpose, and set user_consent to true. Stores the email and the optional use case; see https://deepdna.ai/privacy/.