Aihw MCP vs Openfda
A side-by-side look at the Aihw MCP and Openfda MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.
Verdict: choose Aihw MCP for biology & bioinformatics work as a local process; choose Openfda for biology & bioinformatics as a local process. You can also run both side by side in one mcpServers block.
Which MCP server should you choose?
Choose Aihw MCP when
- You need dedicated capabilities in the Biology & Bioinformatics domain.
- You prefer a local stdio subprocess transport.
- You want tools like
search_datasets, describe_dataset, get_data.
Choose Openfda when
- You need dedicated capabilities in the Biology & Bioinformatics domain.
- You prefer a local stdio subprocess transport.
- You want tools like
fda_drug_events, fda_drug_approvals, fda_applications_by_cik.
Feature & specification comparison
Rows where the two servers differ are marked.
| Spec | ||
|---|---|---|
| Category | Biology & Bioinformatics | Biology & Bioinformatics |
| Quality signal | 55/100 · Good | 60/100 · Good |
| Install command | Confirmed | Confirmed |
| Transport | Local subprocess (stdio) | Local subprocess (stdio) |
| Auth | Not declared | Not declared |
| Pricing | Not declared | Not declared |
| Required env vars | None listed | None listed |
| Verified owner | Community listing | Community listing |
| GitHub stars | 0 | 0 |
| Directory activity | 1 views 0 installs 0 upvotes | 3 views 0 installs 0 upvotes |
| Tools | 6 | 18 |
| Full listing | View Aihw MCP | View Openfda |
Tools & capabilities
Aihw MCP tools 6
search_datasetsFuzzy-search the curated AIHW dataset catalog. All datasets ship hand-curated in v0.1: long-term mortality (GRIM), regional mortality (MORT), cancer incidence and mortality, health expenditure, youth justice detention, and the public hospitals register. Examples: # Find a dataset that gives deaths by cause results = await search_datasets("mortality cause of death") # → [{id: 'GRIM_DEATHS', name: 'GRIM — long-term mortality', ...}] # Discover what's available on cancer results = await search_datasets("cancer") Returns: List of DatasetSummary (id, name, description, update_frequency, is_curated), ranked by relevance.describe_datasetDescribe a dataset's filterable dimensions, returnable measures, units, and source. Use this before calling get_data on a new dataset — it tells you the valid filter keys ('sex', 'year', 'state'), the valid filter values ('Females', 'Males', 'Persons'), the measure aliases ('deaths', 'crude_rate_per_100000'), and the canonical source URL. Returns: DatasetDetail with id, name, description, period_coverage, list of dimensions, list of measures (each with key, source_column, unit, description), and source_url + download_url.get_dataQuery a curated AIHW dataset and return observations. Examples: # Deaths from diabetes, all years and sexes resp = await get_data( "GRIM_DEATHS", filters={"cause_of_death": "Diabetes"}, measures="deaths", ) # Breast cancer incidence in females over time resp = await get_data( "CANCER_INCIDENCE_MORTALITY", filters={"cancer_type": "Breast cancer", "sex": "Female", "type": "Incidence"}, ) # Public hospitals in NSW with peer group "Principal referral" resp = await get_data( "PUBLIC_HOSPITALS", filters={"state": "NSW", "peer_group_name": "Principal referral"}, ) Returns: DataResponse with records (or csv), unit, period bounds, row_count, source URL, and CC-BY attribution.latestReturn the most recent observation(s) per measure for a dataset. For transposed time-series tables this trims to the most-recent period. For wide datasets with a real period, "latest" means the most recent period(s) — keeping ALL entities/dimensions at that period, not an arbitrary N rows. For wide single-year tables with no period variation (most AIHW datasets) it returns the same shape as get_data, capped at `limit` rows so a large register (e.g. PUBLIC_HOSPITALS) doesn't blow the response budget. Truncated responses set DataResponse.truncated_at to the original row count. When the curated YAML declares a `headline_slice`, those filter values are applied automatically so the no-filter call returns ONE canonical headline row (e.g. HEALTH_EXPENDITURE → national total, all areas, all sources). User-supplied filters override the headline_slice per-key — `latest("HEALTH_EXPENDITURE", filters={"state": "NSW"})` keeps the area/source defaults and returns the NSW latest-year total. Examples: # Latest year of GRIM data for All causes combined resp = await latest("GRIM_DEATHS", filters={"cause_of_death": "All causes combined"}) # All ~700 public hospitals (default cap of 50 would otherwise apply) resp = await latest("PUBLIC_HOSPITALS", limit=1000)top_nReturn the N rows with the largest (or smallest) value of a measure. This is the most common agent workflow: "show me the top 10 X by Y". Without this tool, an agent would call get_data, receive the full table, and then sort/slice locally — wasting tokens and turns. top_n does the rank server-side and returns only the requested rows. Examples: # Top 10 causes of death in 2023 (Persons) top_n("GRIM_DEATHS", "deaths", n=10, filters={"sex": "Persons", "year": "2023"}) # 20 SA3 regions with the highest age-standardised mortality top_n("MORT_GEOGRAPHY", "age_standardised_rate_per_100000", filters={"category": "Statistical Area Level 3 (SA3)", "sex": "Persons", "year": "2023"}, n=20) # 5 lowest-funded health expenditure areas in NSW top_n("HEALTH_EXPENDITURE", "real_expenditure_millions", filters={"state": "NSW", "financial_year": "2022-23"}, n=5, direction="bottom") Returns: DataResponse with at most `n` records, sorted by `measure` value in the requested direction. Other fields (period, unit, attribution) match a regular get_data call.list_curatedList every curated dataset ID in this version of aihw-mcp. These are the datasets where get_data accepts plain-English filter keys and returns aliased, well-typed measure columns. Each ID is documented via describe_dataset. Returns: Sorted list of dataset IDs.
Openfda tools 18
fda_drug_eventsSearch FAERS adverse event reports by drug name, MedDRA reaction term, or date range. Returns report counts, reaction types, seriousness levels, and dates. Natural multi-word reaction phrasing is retried against MedDRA preferred-term word order before an empty result is reported. FAERS reports do not establish incidence or causality.fda_drug_approvalsFind FDA-approved drugs by brand name, active ingredient, or application number. To find generic versions of a drug, search by active ingredient using products.active_ingredients.name (NOT openfda.generic_name — that field only works in the label endpoint). IMPORTANT: drug names in the FDA database are stored in UPPERCASE — always pass ingredient and brand names in uppercase (e.g. "APIXABAN" not "apixaban") or you will get 0 results. Returns approval status, sponsor, application number (ANDA = generic, NDA = brand), and application details. There is NO queryable "application_type" field — never add application_type:"ANDA" (it returns 0 results). To limit to generics, search by active ingredient and read the ANDA/NDA prefix on application_number in the results. This endpoint has NO indication/disease field — for "drugs approved to treat <condition>" use fda_drug_labels (which searches indications_and_usage); an indication phrase passed here is silently ignored and matches by drug name only. The response `total` can exceed the 100-row cap on a single page — use `skip` to page past it, and `sort` to get genuinely-newest-first ordering ("most recently approved" is not the default order).fda_applications_by_cikFind ALL Drugs@FDA applications for a company by SEC CIK, ticker, or company name — without needing to know its FDA sponsor_name spelling. Drugs@FDA has no company-ID field: sponsor_name is free text, and one company routinely files under several forms (e.g. Eli Lilly appears as "LILLY", "ELI LILLY AND CO", "ELI LILLY CO", "LILLY RES LABS" — its own SEC-registered name "ELI LILLY AND COMPANY" matches ZERO of them in fda_drug_approvals). This resolves the company via SEC (same identity as the edgar pack), derives its most distinctive name token, and searches Drugs@FDA for every sponsor_name variant containing it in one call — returning the combined application list plus a `sponsor_name_forms` breakdown showing exactly which spellings were found. Use this INSTEAD of guessing sponsor_name strings for fda_drug_approvals when you have (or can resolve) the company's CIK/ticker. For a subsidiary or operating name that isn't itself SEC-listed, resolve to the parent first with edgar's sponsor_to_filer, then pass that CIK here.fda_novel_approvalsMost recent novel drug approvals — the newest drugs approved by the FDA. Use for "what is the most recent novel drug the FDA approved", "latest FDA drug approvals", "recently approved new drugs or biologics this month/year". Returns original NDA/BLA approvals (generics excluded by default) sorted newest-first, with approval date, brand name, active ingredients, sponsor, and application number. Not for label text (fda_drug_labels) or searching a specific known drug (fda_drug_approvals).fda_drug_labelsGet FDA drug labeling (SPL) by drug name OR by INDICATION. This is the tool for "what drugs are approved to treat <condition>" — it searches the indications_and_usage text, which the drugsfda approvals endpoint does NOT carry. Query by brand/generic name (openfda.brand_name:"HUMIRA"), or by indicated use (indications_and_usage:"rheumatoid arthritis"). Returns indications, boxed/other warnings, dosage, contraindications, and adverse reactions (each text field capped, set_id preserved for out-of-band full-label fetch). Note: FDA label publication trails approval by weeks, so a just-approved drug may not have a label yet.fda_drug_recallsSearch FDA drug recalls and enforcement actions by drug name or reason — returns recall classification, date, reason and enforcement status. A multi-word search is tried as ALL terms first and falls back to ANY term when nothing matches all of them; the response says which happened in match_mode, so a loose match is never mistaken for a precise one. Recall reasons are free narrative text and often name the contaminant rather than the harm ("NDMA impurity", not "cancer"), so search the substance when a symptom finds nothing.fda_drug_shortagesSearch the FDA Drug Shortages database by generic or brand name, manufacturer, status, or an advanced openFDA query. Returns national supply records and available FDA dates; reason and other details are sparse in the upstream data. This is not local pharmacy inventory or medical advice.fda_shortage_changesFDA drug-shortage records ordered by update_date, newest first, then restricted to the requested look-back window. Use for recently updated, discontinued, or resolved national shortages; this does not imply availability at any specific pharmacy or hospital. Most rows in any window are "Reverified" (FDA re-checking a status it already had) — pass update_type to filter to the change kinds that actually matter, e.g. New/Discontinued/To Be Discontinued/Resolved, and exclude Reverified.fda_complete_response_lettersSearch FDA-disclosed Complete Response Letters for drug and biologic applications. Defaults to letter_type "COMPLETE RESPONSE"; optionally include other letter types in the same dataset. Returns the application’s current approval_status, letter metadata, an excerpt, and the official document URL.fda_crl_detailRetrieve one FDA Complete Response Letter by application number and optionally letter date. Returns the FDA-disclosed letter text and document URL. Confidential commercial and trade-secret material may be redacted by FDA.fda_food_recallsSearch FDA FOOD recall / enforcement reports (openFDA /food/enforcement) — product recalls, reasons, classification, recalling firm, distribution, and status. Use for food-safety / recall-history questions (distinct from fda_drug_recalls which covers drugs).fda_event_countsAggregate adverse events by reaction type, patient age, or outcome. Returns top reactions for a drug and event trends over time.- +6 more on the listing page
Ready-to-paste client configs
Paste either block (or both) into your client config, e.g. claude_desktop_config.json or ~/.cursor/mcp.json. We only show a config when the install command is confirmed.
Aihw MCP
{
"mcpServers": {
"aihw-mcp": {
"command": "uvx",
"args": [
"--upgrade",
"aihw-mcp"
]
}
}
}
Openfda
{
"mcpServers": {
"openfda": {
"command": "npx",
"args": [
"-y",
"@pipeworx/mcp-openfda"
]
}
}
}
Frequently asked questions
Aihw MCP is categorized under Biology & Bioinformatics and uses a local stdio subprocess. Openfda belongs to Biology & Bioinformatics and uses a local stdio subprocess. Pick Aihw MCP for biology & bioinformatics work and Openfda for biology & bioinformatics.
Copy the mcpServers block from the config section on this page into your client's config (for example claude_desktop_config.json or ~/.cursor/mcp.json), then fully restart the client.
Aihw MCP has no declared pricing — check the project's own site. Openfda has no declared pricing — check the project's own site. If a server needs environment variables such as API keys, define them under the env key in your client's MCP config.
Yes. MCP clients support multiple servers: add aihw-mcp and openfda as separate keys in the same mcpServers object, and your assistant will call tools from either one.
On AllMCPs, Aihw MCP has a quality signal of 55/100 (Good) with 1 views, 0 installs and 0 GitHub stars. Openfda has 60/100 (Good) with 3 views, 0 installs and 0 GitHub stars.