openFDA MCP by usefulapi is an MCP server published by io.usefulapi, hosted at openfda.usefulapi.io. When last checked on 2026-11-22 it was working: it answers and lists its tools. It declares 14 tools, including openfda_search_drug_events, openfda_search_drug_labels, openfda_search_drug_ndc, openfda_search_drug_recalls, openfda_search_drugsfda.
Search openFDA drug, device, food and adverse-event datasets.
4,067 connections through 5 shared values. Tap any node.
Inferred from the host name and headers: what a server runs on, not who runs it.
Search the FDA Adverse Event Reporting System (FAERS): reports of drug side effects, adverse reactions and medication errors submitted to the FDA. Returns individual case reports. openFDA drug/event endpoint.
| Parameter | Type | Description |
|---|---|---|
| skip | integer | Number of records to skip, for pagination (0–25000; skip+limit reaches up to ~26000 records). |
| sort | string | Sort order, as `field:asc` or `field:desc`, e.g. 'receivedate:desc'. |
| limit | integer | Max number of records to return (1–1000). Omit for the API default of 1. |
| search | string | Lucene-style query over this dataset's fields: 'field:term', AND with '+AND+', OR with a space, exact phrase via a '.exact' field suffix with quotes, ranges as '[low+TO+high]' (dates like '[20040101+TO+20081231]'). Example: patient.drug.medicinalproduct:"aspirin" |
None yet. Changes appear after a server's second daily check.
Squares are this server's values; dots are other servers sharing them. A shared address or publisher is a lead, not proof of a common operator.
{
"name": "openfda_search_drug_events",
"title": "Search drug adverse-event reports (FAERS)",
"description": "Search the FDA Adverse Event Reporting System (FAERS): reports of drug side effects, adverse reactions and medication errors submitted to the FDA. Returns individual case reports. openFDA drug/event endpoint.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {
"skip": {
"type": "integer",
"maximum": 25000,
"minimum": 0,
"description": "Number of records to skip, for pagination (0–25000; skip+limit reaches up to ~26000 records)."
},
"sort": {
"type": "string",
"description": "Sort order, as `field:asc` or `field:desc`, e.g. 'receivedate:desc'."
},
"limit": {
"type": "integer",
"maximum": 1000,
"minimum": 1,
"description": "Max number of records to return (1–1000). Omit for the API default of 1."
},
"search": {
"type": "string",
"description": "Lucene-style query over this dataset's fields: 'field:term', AND with '+AND+', OR with a space, exact phrase via a '.exact' field suffix with quotes, ranges as '[low+TO+high]' (dates like '[20040101+TO+20081231]'). Example: patient.drug.medicinalproduct:\"aspirin\""
}
}
},
"annotations": {
"title": "Search drug adverse-event reports (FAERS)",
"readOnlyHint": true
}
}Search Structured Product Labeling (SPL): the official prescribing information for drugs — indications, warnings, dosage, adverse reactions, drug interactions and more. openFDA drug/label endpoint.
| Parameter | Type | Description |
|---|---|---|
| skip | integer | Number of records to skip, for pagination (0–25000; skip+limit reaches up to ~26000 records). |
| sort | string | Sort order, as `field:asc` or `field:desc`, e.g. 'receivedate:desc'. |
| limit | integer | Max number of records to return (1–1000). Omit for the API default of 1. |
| search | string | Lucene-style query over this dataset's fields: 'field:term', AND with '+AND+', OR with a space, exact phrase via a '.exact' field suffix with quotes, ranges as '[low+TO+high]' (dates like '[20040101+TO+20081231]'). Example: openfda.brand_name:"tylenol" |
{
"name": "openfda_search_drug_labels",
"title": "Search drug product labels (SPL)",
"description": "Search Structured Product Labeling (SPL): the official prescribing information for drugs — indications, warnings, dosage, adverse reactions, drug interactions and more. openFDA drug/label endpoint.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {
"skip": {
"type": "integer",
"maximum": 25000,
"minimum": 0,
"description": "Number of records to skip, for pagination (0–25000; skip+limit reaches up to ~26000 records)."
},
"sort": {
"type": "string",
"description": "Sort order, as `field:asc` or `field:desc`, e.g. 'receivedate:desc'."
},
"limit": {
"type": "integer",
"maximum": 1000,
"minimum": 1,
"description": "Max number of records to return (1–1000). Omit for the API default of 1."
},
"search": {
"type": "string",
"description": "Lucene-style query over this dataset's fields: 'field:term', AND with '+AND+', OR with a space, exact phrase via a '.exact' field suffix with quotes, ranges as '[low+TO+high]' (dates like '[20040101+TO+20081231]'). Example: openfda.brand_name:\"tylenol\""
}
}
},
"annotations": {
"title": "Search drug product labels (SPL)",
"readOnlyHint": true
}
}Search the National Drug Code (NDC) directory: every drug product's code, name, dosage form, route, active ingredients, marketing status and labeler. openFDA drug/ndc endpoint.
| Parameter | Type | Description |
|---|---|---|
| skip | integer | Number of records to skip, for pagination (0–25000; skip+limit reaches up to ~26000 records). |
| sort | string | Sort order, as `field:asc` or `field:desc`, e.g. 'receivedate:desc'. |
| limit | integer | Max number of records to return (1–1000). Omit for the API default of 1. |
| search | string | Lucene-style query over this dataset's fields: 'field:term', AND with '+AND+', OR with a space, exact phrase via a '.exact' field suffix with quotes, ranges as '[low+TO+high]' (dates like '[20040101+TO+20081231]'). Example: finished:true+AND+dosage_form:"tablet" |
{
"name": "openfda_search_drug_ndc",
"title": "Search the National Drug Code directory",
"description": "Search the National Drug Code (NDC) directory: every drug product's code, name, dosage form, route, active ingredients, marketing status and labeler. openFDA drug/ndc endpoint.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {
"skip": {
"type": "integer",
"maximum": 25000,
"minimum": 0,
"description": "Number of records to skip, for pagination (0–25000; skip+limit reaches up to ~26000 records)."
},
"sort": {
"type": "string",
"description": "Sort order, as `field:asc` or `field:desc`, e.g. 'receivedate:desc'."
},
"limit": {
"type": "integer",
"maximum": 1000,
"minimum": 1,
"description": "Max number of records to return (1–1000). Omit for the API default of 1."
},
"search": {
"type": "string",
"description": "Lucene-style query over this dataset's fields: 'field:term', AND with '+AND+', OR with a space, exact phrase via a '.exact' field suffix with quotes, ranges as '[low+TO+high]' (dates like '[20040101+TO+20081231]'). Example: finished:true+AND+dosage_form:\"tablet\""
}
}
},
"annotations": {
"title": "Search the National Drug Code directory",
"readOnlyHint": true
}
}Search drug recall enforcement reports: recalled drug products with the reason, classification (Class I/II/III), recalling firm, distribution and status. openFDA drug/enforcement endpoint.
| Parameter | Type | Description |
|---|---|---|
| skip | integer | Number of records to skip, for pagination (0–25000; skip+limit reaches up to ~26000 records). |
| sort | string | Sort order, as `field:asc` or `field:desc`, e.g. 'receivedate:desc'. |
| limit | integer | Max number of records to return (1–1000). Omit for the API default of 1. |
| search | string | Lucene-style query over this dataset's fields: 'field:term', AND with '+AND+', OR with a space, exact phrase via a '.exact' field suffix with quotes, ranges as '[low+TO+high]' (dates like '[20040101+TO+20081231]'). Example: classification:"Class I" |
{
"name": "openfda_search_drug_recalls",
"title": "Search drug recall enforcement reports",
"description": "Search drug recall enforcement reports: recalled drug products with the reason, classification (Class I/II/III), recalling firm, distribution and status. openFDA drug/enforcement endpoint.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {
"skip": {
"type": "integer",
"maximum": 25000,
"minimum": 0,
"description": "Number of records to skip, for pagination (0–25000; skip+limit reaches up to ~26000 records)."
},
"sort": {
"type": "string",
"description": "Sort order, as `field:asc` or `field:desc`, e.g. 'receivedate:desc'."
},
"limit": {
"type": "integer",
"maximum": 1000,
"minimum": 1,
"description": "Max number of records to return (1–1000). Omit for the API default of 1."
},
"search": {
"type": "string",
"description": "Lucene-style query over this dataset's fields: 'field:term', AND with '+AND+', OR with a space, exact phrase via a '.exact' field suffix with quotes, ranges as '[low+TO+high]' (dates like '[20040101+TO+20081231]'). Example: classification:\"Class I\""
}
}
},
"annotations": {
"title": "Search drug recall enforcement reports",
"readOnlyHint": true
}
}Search Drugs@FDA: FDA-approved drug products and their applications (NDA/ANDA/BLA), sponsors, approval dates, products and submissions. openFDA drug/drugsfda endpoint.
| Parameter | Type | Description |
|---|---|---|
| skip | integer | Number of records to skip, for pagination (0–25000; skip+limit reaches up to ~26000 records). |
| sort | string | Sort order, as `field:asc` or `field:desc`, e.g. 'receivedate:desc'. |
| limit | integer | Max number of records to return (1–1000). Omit for the API default of 1. |
| search | string | Lucene-style query over this dataset's fields: 'field:term', AND with '+AND+', OR with a space, exact phrase via a '.exact' field suffix with quotes, ranges as '[low+TO+high]' (dates like '[20040101+TO+20081231]'). Example: openfda.brand_name:"humira" |
{
"name": "openfda_search_drugsfda",
"title": "Search Drugs@FDA approved products",
"description": "Search Drugs@FDA: FDA-approved drug products and their applications (NDA/ANDA/BLA), sponsors, approval dates, products and submissions. openFDA drug/drugsfda endpoint.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {
"skip": {
"type": "integer",
"maximum": 25000,
"minimum": 0,
"description": "Number of records to skip, for pagination (0–25000; skip+limit reaches up to ~26000 records)."
},
"sort": {
"type": "string",
"description": "Sort order, as `field:asc` or `field:desc`, e.g. 'receivedate:desc'."
},
"limit": {
"type": "integer",
"maximum": 1000,
"minimum": 1,
"description": "Max number of records to return (1–1000). Omit for the API default of 1."
},
"search": {
"type": "string",
"description": "Lucene-style query over this dataset's fields: 'field:term', AND with '+AND+', OR with a space, exact phrase via a '.exact' field suffix with quotes, ranges as '[low+TO+high]' (dates like '[20040101+TO+20081231]'). Example: openfda.brand_name:\"humira\""
}
}
},
"annotations": {
"title": "Search Drugs@FDA approved products",
"readOnlyHint": true
}
}Search current and resolved drug shortages: the affected product, status, reason, availability and related dates. openFDA drug/shortages endpoint.
| Parameter | Type | Description |
|---|---|---|
| skip | integer | Number of records to skip, for pagination (0–25000; skip+limit reaches up to ~26000 records). |
| sort | string | Sort order, as `field:asc` or `field:desc`, e.g. 'receivedate:desc'. |
| limit | integer | Max number of records to return (1–1000). Omit for the API default of 1. |
| search | string | Lucene-style query over this dataset's fields: 'field:term', AND with '+AND+', OR with a space, exact phrase via a '.exact' field suffix with quotes, ranges as '[low+TO+high]' (dates like '[20040101+TO+20081231]'). Example: status:"Current" |
{
"name": "openfda_search_drug_shortages",
"title": "Search drug shortages",
"description": "Search current and resolved drug shortages: the affected product, status, reason, availability and related dates. openFDA drug/shortages endpoint.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {
"skip": {
"type": "integer",
"maximum": 25000,
"minimum": 0,
"description": "Number of records to skip, for pagination (0–25000; skip+limit reaches up to ~26000 records)."
},
"sort": {
"type": "string",
"description": "Sort order, as `field:asc` or `field:desc`, e.g. 'receivedate:desc'."
},
"limit": {
"type": "integer",
"maximum": 1000,
"minimum": 1,
"description": "Max number of records to return (1–1000). Omit for the API default of 1."
},
"search": {
"type": "string",
"description": "Lucene-style query over this dataset's fields: 'field:term', AND with '+AND+', OR with a space, exact phrase via a '.exact' field suffix with quotes, ranges as '[low+TO+high]' (dates like '[20040101+TO+20081231]'). Example: status:\"Current\""
}
}
},
"annotations": {
"title": "Search drug shortages",
"readOnlyHint": true
}
}Search the MAUDE database: medical device adverse events — reported injuries, deaths and malfunctions involving medical devices. openFDA device/event endpoint.
| Parameter | Type | Description |
|---|---|---|
| skip | integer | Number of records to skip, for pagination (0–25000; skip+limit reaches up to ~26000 records). |
| sort | string | Sort order, as `field:asc` or `field:desc`, e.g. 'receivedate:desc'. |
| limit | integer | Max number of records to return (1–1000). Omit for the API default of 1. |
| search | string | Lucene-style query over this dataset's fields: 'field:term', AND with '+AND+', OR with a space, exact phrase via a '.exact' field suffix with quotes, ranges as '[low+TO+high]' (dates like '[20040101+TO+20081231]'). Example: device.generic_name:"pacemaker" |
{
"name": "openfda_search_device_events",
"title": "Search device adverse-event reports (MAUDE)",
"description": "Search the MAUDE database: medical device adverse events — reported injuries, deaths and malfunctions involving medical devices. openFDA device/event endpoint.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {
"skip": {
"type": "integer",
"maximum": 25000,
"minimum": 0,
"description": "Number of records to skip, for pagination (0–25000; skip+limit reaches up to ~26000 records)."
},
"sort": {
"type": "string",
"description": "Sort order, as `field:asc` or `field:desc`, e.g. 'receivedate:desc'."
},
"limit": {
"type": "integer",
"maximum": 1000,
"minimum": 1,
"description": "Max number of records to return (1–1000). Omit for the API default of 1."
},
"search": {
"type": "string",
"description": "Lucene-style query over this dataset's fields: 'field:term', AND with '+AND+', OR with a space, exact phrase via a '.exact' field suffix with quotes, ranges as '[low+TO+high]' (dates like '[20040101+TO+20081231]'). Example: device.generic_name:\"pacemaker\""
}
}
},
"annotations": {
"title": "Search device adverse-event reports (MAUDE)",
"readOnlyHint": true
}
}Search 510(k) premarket notification clearances: devices cleared for market as substantially equivalent to a predicate, with applicant, decision, product code and dates. openFDA device/510k endpoint.
| Parameter | Type | Description |
|---|---|---|
| skip | integer | Number of records to skip, for pagination (0–25000; skip+limit reaches up to ~26000 records). |
| sort | string | Sort order, as `field:asc` or `field:desc`, e.g. 'receivedate:desc'. |
| limit | integer | Max number of records to return (1–1000). Omit for the API default of 1. |
| search | string | Lucene-style query over this dataset's fields: 'field:term', AND with '+AND+', OR with a space, exact phrase via a '.exact' field suffix with quotes, ranges as '[low+TO+high]' (dates like '[20040101+TO+20081231]'). Example: openfda.device_name:"catheter" |
{
"name": "openfda_search_device_510k",
"title": "Search 510(k) premarket clearances",
"description": "Search 510(k) premarket notification clearances: devices cleared for market as substantially equivalent to a predicate, with applicant, decision, product code and dates. openFDA device/510k endpoint.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {
"skip": {
"type": "integer",
"maximum": 25000,
"minimum": 0,
"description": "Number of records to skip, for pagination (0–25000; skip+limit reaches up to ~26000 records)."
},
"sort": {
"type": "string",
"description": "Sort order, as `field:asc` or `field:desc`, e.g. 'receivedate:desc'."
},
"limit": {
"type": "integer",
"maximum": 1000,
"minimum": 1,
"description": "Max number of records to return (1–1000). Omit for the API default of 1."
},
"search": {
"type": "string",
"description": "Lucene-style query over this dataset's fields: 'field:term', AND with '+AND+', OR with a space, exact phrase via a '.exact' field suffix with quotes, ranges as '[low+TO+high]' (dates like '[20040101+TO+20081231]'). Example: openfda.device_name:\"catheter\""
}
}
},
"annotations": {
"title": "Search 510(k) premarket clearances",
"readOnlyHint": true
}
}Search medical device recalls: recalled devices with the reason, recalling firm, classification, product code and status. openFDA device/recall endpoint.
| Parameter | Type | Description |
|---|---|---|
| skip | integer | Number of records to skip, for pagination (0–25000; skip+limit reaches up to ~26000 records). |
| sort | string | Sort order, as `field:asc` or `field:desc`, e.g. 'receivedate:desc'. |
| limit | integer | Max number of records to return (1–1000). Omit for the API default of 1. |
| search | string | Lucene-style query over this dataset's fields: 'field:term', AND with '+AND+', OR with a space, exact phrase via a '.exact' field suffix with quotes, ranges as '[low+TO+high]' (dates like '[20040101+TO+20081231]'). Example: product_res_number:"Z-1234-2019" |
{
"name": "openfda_search_device_recalls",
"title": "Search device recalls",
"description": "Search medical device recalls: recalled devices with the reason, recalling firm, classification, product code and status. openFDA device/recall endpoint.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {
"skip": {
"type": "integer",
"maximum": 25000,
"minimum": 0,
"description": "Number of records to skip, for pagination (0–25000; skip+limit reaches up to ~26000 records)."
},
"sort": {
"type": "string",
"description": "Sort order, as `field:asc` or `field:desc`, e.g. 'receivedate:desc'."
},
"limit": {
"type": "integer",
"maximum": 1000,
"minimum": 1,
"description": "Max number of records to return (1–1000). Omit for the API default of 1."
},
"search": {
"type": "string",
"description": "Lucene-style query over this dataset's fields: 'field:term', AND with '+AND+', OR with a space, exact phrase via a '.exact' field suffix with quotes, ranges as '[low+TO+high]' (dates like '[20040101+TO+20081231]'). Example: product_res_number:\"Z-1234-2019\""
}
}
},
"annotations": {
"title": "Search device recalls",
"readOnlyHint": true
}
}Search the FDA device classification database: a device type's product code, device class (I/II/III), regulation number, medical specialty and submission requirements. openFDA device/classification endpoint.
| Parameter | Type | Description |
|---|---|---|
| skip | integer | Number of records to skip, for pagination (0–25000; skip+limit reaches up to ~26000 records). |
| sort | string | Sort order, as `field:asc` or `field:desc`, e.g. 'receivedate:desc'. |
| limit | integer | Max number of records to return (1–1000). Omit for the API default of 1. |
| search | string | Lucene-style query over this dataset's fields: 'field:term', AND with '+AND+', OR with a space, exact phrase via a '.exact' field suffix with quotes, ranges as '[low+TO+high]' (dates like '[20040101+TO+20081231]'). Example: medical_specialty_description:"Cardiovascular" |
{
"name": "openfda_search_device_classification",
"title": "Search device classification",
"description": "Search the FDA device classification database: a device type's product code, device class (I/II/III), regulation number, medical specialty and submission requirements. openFDA device/classification endpoint.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {
"skip": {
"type": "integer",
"maximum": 25000,
"minimum": 0,
"description": "Number of records to skip, for pagination (0–25000; skip+limit reaches up to ~26000 records)."
},
"sort": {
"type": "string",
"description": "Sort order, as `field:asc` or `field:desc`, e.g. 'receivedate:desc'."
},
"limit": {
"type": "integer",
"maximum": 1000,
"minimum": 1,
"description": "Max number of records to return (1–1000). Omit for the API default of 1."
},
"search": {
"type": "string",
"description": "Lucene-style query over this dataset's fields: 'field:term', AND with '+AND+', OR with a space, exact phrase via a '.exact' field suffix with quotes, ranges as '[low+TO+high]' (dates like '[20040101+TO+20081231]'). Example: medical_specialty_description:\"Cardiovascular\""
}
}
},
"annotations": {
"title": "Search device classification",
"readOnlyHint": true
}
}Search the CFSAN Adverse Event Reporting System (CAERS): adverse events and product complaints for foods, dietary supplements and cosmetics. openFDA food/event endpoint.
| Parameter | Type | Description |
|---|---|---|
| skip | integer | Number of records to skip, for pagination (0–25000; skip+limit reaches up to ~26000 records). |
| sort | string | Sort order, as `field:asc` or `field:desc`, e.g. 'receivedate:desc'. |
| limit | integer | Max number of records to return (1–1000). Omit for the API default of 1. |
| search | string | Lucene-style query over this dataset's fields: 'field:term', AND with '+AND+', OR with a space, exact phrase via a '.exact' field suffix with quotes, ranges as '[low+TO+high]' (dates like '[20040101+TO+20081231]'). Example: products.industry_name:"Dietary Conventional Foods/Meal Replacements" |
{
"name": "openfda_search_food_events",
"title": "Search food/supplement/cosmetic adverse events (CAERS)",
"description": "Search the CFSAN Adverse Event Reporting System (CAERS): adverse events and product complaints for foods, dietary supplements and cosmetics. openFDA food/event endpoint.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {
"skip": {
"type": "integer",
"maximum": 25000,
"minimum": 0,
"description": "Number of records to skip, for pagination (0–25000; skip+limit reaches up to ~26000 records)."
},
"sort": {
"type": "string",
"description": "Sort order, as `field:asc` or `field:desc`, e.g. 'receivedate:desc'."
},
"limit": {
"type": "integer",
"maximum": 1000,
"minimum": 1,
"description": "Max number of records to return (1–1000). Omit for the API default of 1."
},
"search": {
"type": "string",
"description": "Lucene-style query over this dataset's fields: 'field:term', AND with '+AND+', OR with a space, exact phrase via a '.exact' field suffix with quotes, ranges as '[low+TO+high]' (dates like '[20040101+TO+20081231]'). Example: products.industry_name:\"Dietary Conventional Foods/Meal Replacements\""
}
}
},
"annotations": {
"title": "Search food/supplement/cosmetic adverse events (CAERS)",
"readOnlyHint": true
}
}Search food recall enforcement reports: recalled food products with the reason, classification (Class I/II/III), recalling firm, distribution state and status. openFDA food/enforcement endpoint.
| Parameter | Type | Description |
|---|---|---|
| skip | integer | Number of records to skip, for pagination (0–25000; skip+limit reaches up to ~26000 records). |
| sort | string | Sort order, as `field:asc` or `field:desc`, e.g. 'receivedate:desc'. |
| limit | integer | Max number of records to return (1–1000). Omit for the API default of 1. |
| search | string | Lucene-style query over this dataset's fields: 'field:term', AND with '+AND+', OR with a space, exact phrase via a '.exact' field suffix with quotes, ranges as '[low+TO+high]' (dates like '[20040101+TO+20081231]'). Example: state:"CA" |
{
"name": "openfda_search_food_recalls",
"title": "Search food recall enforcement reports",
"description": "Search food recall enforcement reports: recalled food products with the reason, classification (Class I/II/III), recalling firm, distribution state and status. openFDA food/enforcement endpoint.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {
"skip": {
"type": "integer",
"maximum": 25000,
"minimum": 0,
"description": "Number of records to skip, for pagination (0–25000; skip+limit reaches up to ~26000 records)."
},
"sort": {
"type": "string",
"description": "Sort order, as `field:asc` or `field:desc`, e.g. 'receivedate:desc'."
},
"limit": {
"type": "integer",
"maximum": 1000,
"minimum": 1,
"description": "Max number of records to return (1–1000). Omit for the API default of 1."
},
"search": {
"type": "string",
"description": "Lucene-style query over this dataset's fields: 'field:term', AND with '+AND+', OR with a space, exact phrase via a '.exact' field suffix with quotes, ranges as '[low+TO+high]' (dates like '[20040101+TO+20081231]'). Example: state:\"CA\""
}
}
},
"annotations": {
"title": "Search food recall enforcement reports",
"readOnlyHint": true
}
}openFDA's most valuable feature: aggregate over any dataset by a field to get a top-terms histogram (returns `results: [{term, count}]` instead of records). Use the '.exact' field suffix to count whole phrases. Example: endpoint 'drug/event', field 'patient.reaction.reactionmeddrapt.exact', search 'patient.drug.medicinalproduct:"aspirin"' → the most common reactions reported for aspirin.
| Parameter | Type | Description |
|---|---|---|
| field * | string | The field to count/aggregate on (required), e.g. 'patient.reaction.reactionmeddrapt.exact' or 'classification'. Add '.exact' to count whole phrases rather than tokens. |
| limit | integer | Max number of distinct terms to return (1–1000). |
| search | string | Optional Lucene filter applied before aggregation (same syntax as the search tools). |
| endpoint * | string | The openFDA endpoint to query, e.g. 'drug/event', 'device/510k', 'food/enforcement'. |
{
"name": "openfda_count",
"title": "Count/aggregate over an openFDA dataset",
"description": "openFDA's most valuable feature: aggregate over any dataset by a field to get a top-terms histogram (returns `results: [{term, count}]` instead of records). Use the '.exact' field suffix to count whole phrases. Example: endpoint 'drug/event', field 'patient.reaction.reactionmeddrapt.exact', search 'patient.drug.medicinalproduct:\"aspirin\"' → the most common reactions reported for aspirin.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"endpoint",
"field"
],
"properties": {
"field": {
"type": "string",
"description": "The field to count/aggregate on (required), e.g. 'patient.reaction.reactionmeddrapt.exact' or 'classification'. Add '.exact' to count whole phrases rather than tokens."
},
"limit": {
"type": "integer",
"maximum": 1000,
"minimum": 1,
"description": "Max number of distinct terms to return (1–1000)."
},
"search": {
"type": "string",
"description": "Optional Lucene filter applied before aggregation (same syntax as the search tools)."
},
"endpoint": {
"enum": [
"drug/event",
"drug/label",
"drug/ndc",
"drug/enforcement",
"drug/drugsfda",
"drug/shortages",
"drug/orangebook",
"device/event",
"device/510k",
"device/classification",
"device/enforcement",
"device/pma",
"device/recall",
"device/registrationlisting",
"device/udi",
"device/covid19serology",
"food/enforcement",
"food/event",
"other/nsde",
"other/substance",
"tobacco/problem"
],
"type": "string",
"description": "The openFDA endpoint to query, e.g. 'drug/event', 'device/510k', 'food/enforcement'."
}
}
},
"annotations": {
"title": "Count/aggregate over an openFDA dataset",
"readOnlyHint": true
}
}Generic escape hatch to query ANY supported openFDA endpoint with the full parameter set — covers the less-common datasets (device/pma, device/registrationlisting, device/udi, device/covid19serology, drug/orangebook, other/nsde, other/substance, tobacco/problem, etc.). Use the named search tools for the common datasets; use this for everything else or for advanced queries. openFDA REST API.
| Parameter | Type | Description |
|---|---|---|
| skip | integer | Number of records to skip, for pagination (0–25000; skip+limit reaches up to ~26000 records). |
| sort | string | Sort order, as `field:asc` or `field:desc`, e.g. 'receivedate:desc'. |
| count | string | Optional field to aggregate on (returns `results: [{term, count}]`); add '.exact' for whole phrases. |
| limit | integer | Max number of records to return (1–1000). Omit for the API default of 1. |
| search | string | Lucene-style query over this dataset's fields: 'field:term', AND with '+AND+', OR with a space, exact phrase via a '.exact' field suffix with quotes, ranges as '[low+TO+high]' (dates like '[20040101+TO+20081231]'). Example: e.g. brand_name:"x" (fields vary by endpoint) |
| endpoint * | string | The openFDA endpoint to query, e.g. 'drug/event', 'device/510k', 'food/enforcement'. |
{
"name": "openfda_query",
"title": "Query any openFDA endpoint (generic)",
"description": "Generic escape hatch to query ANY supported openFDA endpoint with the full parameter set — covers the less-common datasets (device/pma, device/registrationlisting, device/udi, device/covid19serology, drug/orangebook, other/nsde, other/substance, tobacco/problem, etc.). Use the named search tools for the common datasets; use this for everything else or for advanced queries. openFDA REST API.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"endpoint"
],
"properties": {
"skip": {
"type": "integer",
"maximum": 25000,
"minimum": 0,
"description": "Number of records to skip, for pagination (0–25000; skip+limit reaches up to ~26000 records)."
},
"sort": {
"type": "string",
"description": "Sort order, as `field:asc` or `field:desc`, e.g. 'receivedate:desc'."
},
"count": {
"type": "string",
"description": "Optional field to aggregate on (returns `results: [{term, count}]`); add '.exact' for whole phrases."
},
"limit": {
"type": "integer",
"maximum": 1000,
"minimum": 1,
"description": "Max number of records to return (1–1000). Omit for the API default of 1."
},
"search": {
"type": "string",
"description": "Lucene-style query over this dataset's fields: 'field:term', AND with '+AND+', OR with a space, exact phrase via a '.exact' field suffix with quotes, ranges as '[low+TO+high]' (dates like '[20040101+TO+20081231]'). Example: e.g. brand_name:\"x\" (fields vary by endpoint)"
},
"endpoint": {
"enum": [
"drug/event",
"drug/label",
"drug/ndc",
"drug/enforcement",
"drug/drugsfda",
"drug/shortages",
"drug/orangebook",
"device/event",
"device/510k",
"device/classification",
"device/enforcement",
"device/pma",
"device/recall",
"device/registrationlisting",
"device/udi",
"device/covid19serology",
"food/enforcement",
"food/event",
"other/nsde",
"other/substance",
"tobacco/problem"
],
"type": "string",
"description": "The openFDA endpoint to query, e.g. 'drug/event', 'device/510k', 'food/enforcement'."
}
}
},
"annotations": {
"title": "Query any openFDA endpoint (generic)",
"readOnlyHint": true
}
}Tools for openFDA, hosted by usefulapi.io. If the user is new or asks what this server can do, suggest requests such as: "What are the most commonly reported side effects of ibuprofen?"; "Have there been any Class I food recalls for peanut products recently?"; "Is amoxicillin currently listed as a drug shortage, and what is the reason?". Read-only tools never change data; ask the user before a tool that creates, changes or deletes openFDA data. Free plan: 50 tool calls per month. Run openfda_usage_status to see the calls used this month. If the user asks for something none of these tools can do, tell the user and, with their OK, run openfda_request_feature to record the request. Paid plans: Pro (10,000 tool calls a month, $9/month or $90/year, for normal use) and Pro+ (100,000 tool calls a month, $39/month or $390/year, for automations and heavy use). A plan can be cancelled at any time and then runs to the end of the paid period, so it also suits a one-time job. When the user wants more calls or reaches the limit, run openfda_upgrade without a plan: it returns both plans, each with a payment link for the user to open. openfda_cancel_subscription cancels Pro at the end of the paid period.
Names, descriptions and schemas were written by the server and are shown as data.
Shared addresses on big platforms (Cloudflare, Vercel and the like) put unrelated servers together; those are marked shared_infrastructure. A match is a pivot, not a link between operators.