{ "openapi": "3.0.1", "info": { "title": "Socrata Open Data Scraper: Gov Datasets", "description": "Search and pull datasets from any Socrata government portal (CDC, HHS, CMS, NY, NYC, Texas, 100s more). SoQL filtered queries, structured JSON, no API key, no anti bot. Works in Claude, ChatGPT and any MCP agent for instant public data access.", "version": "0.1", "x-build-id": "HekryjGdfkrpM32fX" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/themineworks~socrata-open-data/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-themineworks-socrata-open-data", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/themineworks~socrata-open-data/runs": { "post": { "operationId": "runs-sync-themineworks-socrata-open-data", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/themineworks~socrata-open-data/run-sync": { "post": { "operationId": "run-sync-themineworks-socrata-open-data", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } } }, "components": { "schemas": { "inputSchema": { "type": "object", "properties": { "searchQuery": { "title": "Search datasets (discovery mode)", "type": "string", "description": "Find datasets across ALL Socrata portals by keyword (e.g. covid deaths, restaurant inspections, trade). Leave domain + datasetId blank to use this mode and get a catalog of matching datasets with their domain + id." }, "domain": { "title": "Portal domain (data mode)", "type": "string", "description": "The Socrata portal domain to pull rows from, e.g. data.cdc.gov, data.ny.gov, data.cityofnewyork.us. Provide together with datasetId." }, "datasetId": { "title": "Dataset ID (data mode)", "type": "string", "description": "The dataset's 4x4 identifier, e.g. 9bhg-hcku. Find it via discovery mode or in the dataset's URL." }, "where": { "title": "Filter (SoQL $where)", "type": "string", "description": "Optional SoQL filter, e.g. state='New York' AND covid_19_deaths > 100" }, "select": { "title": "Fields (SoQL $select)", "type": "string", "description": "Optional comma-separated fields to return, e.g. state,sex,age_group,covid_19_deaths. Leave blank for all fields." }, "order": { "title": "Sort (SoQL $order)", "type": "string", "description": "Optional sort, e.g. covid_19_deaths DESC" }, "appToken": { "title": "Socrata app token (optional)", "type": "string", "description": "A free Socrata app token raises rate limits. Leave blank for keyless access (lower limits, fine for most runs)." }, "maxResults": { "title": "Max records", "minimum": 1, "maximum": 100000, "type": "integer", "description": "Maximum number of records (rows or datasets) to return.", "default": 1000 } } }, "runsResponseSchema": { "type": "object", "properties": { "data": { "type": "object", "properties": { "id": { "type": "string" }, "actId": { "type": "string" }, "userId": { "type": "string" }, "startedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "finishedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "status": { "type": "string", "example": "READY" }, "meta": { "type": "object", "properties": { "origin": { "type": "string", "example": "API" }, "userAgent": { "type": "string" } } }, "stats": { "type": "object", "properties": { "inputBodyLen": { "type": "integer", "example": 2000 }, "rebootCount": { "type": "integer", "example": 0 }, "restartCount": { "type": "integer", "example": 0 }, "resurrectCount": { "type": "integer", "example": 0 }, "computeUnits": { "type": "integer", "example": 0 } } }, "options": { "type": "object", "properties": { "build": { "type": "string", "example": "latest" }, "timeoutSecs": { "type": "integer", "example": 300 }, "memoryMbytes": { "type": "integer", "example": 1024 }, "diskMbytes": { "type": "integer", "example": 2048 } } }, "buildId": { "type": "string" }, "defaultKeyValueStoreId": { "type": "string" }, "defaultDatasetId": { "type": "string" }, "defaultRequestQueueId": { "type": "string" }, "buildNumber": { "type": "string", "example": "1.0.0" }, "containerUrl": { "type": "string" }, "usage": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "integer", "example": 1 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 } } }, "usageTotalUsd": { "type": "number", "example": 0.00005 }, "usageUsd": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "number", "example": 0.00005 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 } } } } } } } } } }