PGxAI Andromeda is an educational reference tool for exploring published drug-drug interactions, gene-drug associations, and drug-disease interactions.
View relevant excerpts from FDA drug labeling and other referenced sources, with links to the original documents. Learn about documented interactions and how genetic variants and metabolizer phenotypes relate to drug metabolism.
Scored across 2 tools
The two tools have clearly distinct roles: get_condition_category is a controlled-vocabulary lookup that feeds review_medication_evidence, which does the actual evidence retrieval. The descriptions explicitly state the dependency and ordering, leaving no realistic chance of misselection.
Both names use snake_case with a verb-first structure (get_/review_) followed by a noun phrase, so the convention is predictable. The minor deviation is that 'get_condition_category' is a three-part lookup name while 'review_medication_evidence' reads as a single compound action, but this does not impair readability.
Two tools is thin even for a narrow evidence-lookup server, though each clearly earns its place as the query tool and its required vocabulary helper. A modest surface like gene/phenotype resolution would make the count feel better scoped.
Disease and population terms are well covered via get_condition_category, which maps user topics to accepted names. However, there is no equivalent helper for genes or genotypes (users must supply an already-interpreted genotype) and no drug-name resolution tool, so agents can hit dead ends when the gene side of a PGx query is ambiguous.
Look up the exact condition names that review_medication_evidence accepts for a disease, risk factor or population topic. Pass the top-level category that best matches the topic; the tool returns that category's sub-codes, each with an exact "name" and a reference icd10_code. A population label with no sub-codes (for example "Asian patients") returns an empty list, which is expected, not an error.
When to use: before calling review_medication_evidence with conditions, call this tool once for EACH disease, risk factor or population term the user mentioned, independently, not all with the same category.
Choosing the name: prefer the most specific sub-code name that matches (hypertension -> "Essential (primary) hypertension", not the category "Cardiovascular disorders"). Use a category name as-is only for a general topic (such as "Hepatic impairment") or when no sub-code fits. Submit the name string, never the icd10_code.
Categories: Adolescent patients 12 to 17 years of age, Asian patients, BMI, Cardiac disorders, Cardiac patients, Cardiovascular disorders, Children 1 year through 16 years of age, Children under 6 months, Cirrhotics, Diabetes, Diabetes mellitus, Female patients, Females of reproductive potential, Females of reproductive potential contraception, Geriatric use, Heart failure, Hemodialysis, Hepatic disease, Hepatic impairment, Immunocompromised patients, Labor and delivery, Lactation / nursing mothers, Liver transplant recipients, Low body weight, Male patients, Males of reproductive potential, Males of reproductive potential contraception, Neonates to less than one year of age, Neuromuscular disease, Neurovascular disorders, Obese patients, Patients after organ transplantation, Patients with compromised respiratory function, Pediatric Patients 6 to 11 Years of Age, Pediatric Patients Younger than 4 Months of Age, Pediatric use, Percutaneous coronary intervention, Pregnancy, Pulmonary patients, Race or ethnicity, Renal impairment, Smoking, Special populations, Type 2 diabetes mellitus, Weight.
Inputs: category (required). Returns: object
Look up published drug-drug interactions (DDI), gene-drug associations (PGx) and drug-disease information (DCI). Use for general reference questions involving two or more drugs, one drug and a named disease or population term, or one drug and an explicitly supplied interpreted gene genotype or phenotype. Provide drug names in English, or a known RxNorm identifier for a drug; when the route of administration is known, give it in parentheses after the name, for example "tacrolimus (topical)" or "furosemide (oral)", using only one of: oral, topical, injectable, ophthalmic, nasal, inhalant, dental, rectal, transdermal, vaginal, otic, buccal, sublingual, irrigation, intravesical, drug implant, mucosal, pyelocalyceal, intraperitoneal; when it is not stated, send the drug name alone and do not guess a route. Send at most 20 medications per request (split a longer list into several requests); map each disease or population term with get_condition_category first and submit the most specific matching sub-code name from it (a category name only for a general topic). If genes is omitted, no gene-drug analysis is performed.
Returns a status, counts, notices and findings with source links; source_url, phenotype and implications may be null.
findings means findings were returned. checked_no_findings means the lookup completed without a returned finding; it is not proof that published evidence is absent or that use is universally safe. nothing_to_check means no medications were submitted. no_data_returned is inconclusive.
The finding severity uses a shared nominal value and is not a ranking of importance. Preserve the cited evidence and its limitations when explaining results.
Inputs: drugs (required), genes, conditions, confirm_no_direct_identifiers. Returns: object
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Add one secure layer between your agents and this server.
