Minds Research API
The Research API from Minds — 5 operation(s) for research.
Work with this as data
Every API here is available over the APIs.io API and to AI agents over MCP.
MCP server
One button, every client — Claude, Cursor, VS Code and the rest.
https://apis.io/mcp
Tools for apis
7 MCP tools reach this
find_apisBrowse and filter every API in the catalog.get_api_artifactsOne API's artifacts, grouped by type.get_openapiThe primary OpenAPI for this API.find_similar_apisAPIs that look like this one.apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.resolveTurn a domain, URL or GitHub org into the provider it belongs to.find_cohortsEvery scored population of providers in the catalog.
Call it yourself
curl for this page
This API
curl "https://apis.io/api/v1/apis/getminds:getminds-research-api"
All apis
curl "https://apis.io/api/v1/apis?limit=25"Discovery needs no key. Ratings and market analysis are Pro.
Get an API key
Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. See our Privacy Policy and Terms.
A second provider on the same verified email joins the account you already have.
OpenAPI Specification
openapi: 3.2.0
info:
title: Minds Public Research API
version: v1
description: 'OpenAPI 3.1.0 spec for the Minds public API (https://getminds.ai/api/v1 / https://api.getminds.ai/v1). Generate a typed TypeScript client by running an OpenAPI generator (e.g. `openapi-typescript`) against `/_openapi.json`. Auth: send `Authorization: Bearer minds_…_key`; create keys in Settings → API Keys.'
servers:
- url: https://api.getminds.ai
description: Production (api subdomain)
- url: https://getminds.ai
description: Production (apex)
security:
- ApiKeyAuth: []
tags:
- name: Research
paths:
/api/v1/research-methods:
get:
parameters: []
responses:
'200':
description: Versioned research methods.
content:
application/json:
schema:
type: object
required:
- data
properties:
data:
type: array
items:
type: object
'401':
description: Missing or invalid authentication.
operationId: listResearchMethods
summary: List research methods
description: Return the versioned research-method catalog, explicit executable state, availability, configuration JSON Schemas, semantic output types, and fallback methods. Experimental and planned methods are visible for framework compatibility but cannot be executed.
tags:
- Research
security:
- ApiKeyAuth: []
/api/v1/studies/{studyId}/research-plans/preview:
post:
parameters:
- in: path
name: studyId
required: true
schema:
type: string
format: uuid
responses:
'200':
description: Saved plan draft, per-question response contracts, and confirmation questions.
content:
application/json:
schema:
type: object
required:
- data
properties:
data:
type: object
properties: {}
'400':
description: Invalid request.
'401':
description: Unauthorized.
'403':
description: Study access denied.
'404':
description: Study or draft not found.
'409':
description: Draft revision conflict.
operationId: previewStudyResearchPlan
summary: Preview or revise a study research plan
description: 'Let the research-planning model capture intent, main source, all attached assets, questions, optional methods, semantic outputs, missing inputs, confirmation questions, and a proposed response contract for every question. Clients can deterministically edit response formats and assign durable assets to exact questions. Pass `questions` instead of `request` to transcribe a fixed instrument exactly: text, order, ids, and per-item response contracts are stored as given and no planning model runs. Fetchable remote files are copied into durable Minds chat storage before the versioned draft is saved. Local file:// paths are not uploads. This endpoint never executes research.'
tags:
- Research
security:
- ApiKeyAuth: []
requestBody:
required: true
content:
application/json:
schema:
type: object
properties:
loadLatest:
type: boolean
description: Read the latest owned draft without planning or saving. Requires draftPlanId; cannot be combined with edits or planner inputs.
edits:
type: object
description: Deterministic edits to a saved revision. Preserves methods and source policy; cannot be combined with planner inputs.
additionalProperties: false
properties:
objective:
type: string
maxLength: 2000
promptContent:
type: string
maxLength: 20000
questions:
type: array
minItems: 1
maxItems: 200
items:
type: object
additionalProperties: false
required:
- id
- moduleId
- text
- response
properties:
id:
type: string
moduleId:
type: string
text:
type: string
maxLength: 2000
attachmentIds:
type: array
items:
type: string
request:
type: string
studyLocale:
type: string
enum:
- en
- es
- fr
- de
- zh
- tr
- ar
- ja
- ko
description: Language used for the plan and its eventual study output.
sourcePolicy:
type: string
enum:
- request_only
- auto
default: request_only
description: Evidence policy stored in this exact draft revision. request_only keeps a controlled Study closed to retrieved Mind documents and live web. auto is an explicit experimental opt-in to relevant Mind-knowledge retrieval; response-mode rules still control live web search.
mindSourcePolicyOverrides:
type: array
maxItems: 2000
description: Experimental checksum-locked Mind assignments. Each Mind UUID may appear once. Unlisted Minds use sourcePolicy; persisted knowledge_only locks remain stricter.
items:
type: object
required:
- mindId
- sourcePolicy
additionalProperties: false
properties:
mindId:
type: string
format: uuid
sourcePolicy:
type: string
enum:
- request_only
- auto
source:
type: object
description: The main source. Prompt content is exact respondent-visible material and is separate from planner-only request text.
properties:
kind:
type: string
enum:
- prompt
- website
- image
- video
- document
- questionnaire
- other
label:
type: string
url:
type: string
format: uri
mimeType:
type: string
content:
type: string
attachments:
type: array
description: Files and website assets available to the confirmed run (one question block). Multi-asset blocks require complete question assignments and coverage of every asset; each question receives only its own assets. Empty lists explicitly mean no assets. Remote file URLs are durably imported; kind website remains a website.
items:
type: object
properties:
kind:
type: string
enum:
- website
id:
type: string
name:
type: string
url:
type: string
path:
type: string
mimeType:
type: string
type:
type: string
questionAttachments:
type: array
description: One-based question-to-attachment-id mapping. Multi-asset blocks require every question to be mapped and every asset to be used. Empty attachmentIds means no assets. Each question may appear at most once.
items:
type: object
required:
- questionNumber
- attachmentIds
additionalProperties: false
properties:
questionNumber:
type: integer
minimum: 1
attachmentIds:
type: array
minItems: 0
uniqueItems: true
items:
type: string
suggestQuestionStimuli:
type: boolean
description: Default true. Lets the planner assign each attached file or website to one or more questions; the ids appear as attachmentIds on those questions. Pass false to keep questions unassigned unless questionAttachments names them.
draftPlanId:
type: string
format: uuid
revision:
type: integer
minimum: 1
refinement:
type: string
answers:
type: object
additionalProperties:
type: string
questionResponses:
type: object
description: Explicit response-format edits keyed by question ID from the current draft.
idempotencyKey:
type: string
maxLength: 200
description: 'Retry-safety key. A repeated preview with the same key returns the draft revision the first attempt saved (`replayed: true`) instead of planning again. The `Idempotency-Key` header takes precedence.'
/api/v1/studies/{studyId}/research-runs/{runId}:
get:
parameters:
- in: path
name: studyId
required: true
schema:
type: string
format: uuid
- in: path
name: runId
required: true
schema:
type: string
format: uuid
responses:
'200':
description: Durable study status and immutable response contracts.
content:
application/json:
schema:
type: object
required:
- data
properties:
data:
type: object
properties:
status:
type: string
enum:
- queued
- running
- completed
- partial
- failed
- cancelled
- plan_limited
description: Partial means settled questions have missing respondent answers or some questions failed. It is terminal collection, not complete evidence.
progress:
type: object
properties:
total:
type: integer
settled:
type: integer
failed:
type: integer
partial:
type: integer
description: Questions with recorded incomplete respondent coverage.
skipped:
type: integer
pct:
type: integer
description: Settled-question progress, not respondent coverage.
respondentStimulusDelivery:
type: object
description: Configured stimulus channel, not proof of delivery. The frozen base Mind profile excludes per-run stimulus.
properties:
channel:
type: string
enum:
- prompt_evidence
- website_analysis
- file_analysis
- none
mindProfileIncludesStimulus:
type: boolean
enum: []
verification:
type: string
enum:
- configuration_only
description:
type: string
respondentMediaEvidence:
type: object
description: Per-Mind video evidence audit. Verified means every recorded answer for every video question has matching audiovisual receipts and accepted-call SDK media prompt hashes.
properties:
version:
type: string
enum:
- respondent-media-evidence-v1
status:
type: string
enum:
- not_applicable
- verified
- incomplete
videoQuestionCount:
type: integer
answerCount:
type: integer
verifiedAnswerCount:
type: integer
visualContract:
type: string
enum:
- scene-sampled-frames
speechContract:
type: string
enum:
- full-transcript
soundtrackContract:
type: string
enum:
- bounded-analysis
failures:
type: array
items:
type: object
additionalProperties: true
questionAttachments:
type: array
items:
type: object
additionalProperties: true
calculations:
type: array
items:
type: object
additionalProperties: true
'401':
description: Unauthorized.
'403':
description: Study access denied.
'404':
description: Study not found.
operationId: getStudyResearchStudy
summary: Get research study status
description: Return durable progress, the immutable confirmed plan snapshot with per-question response contracts, response artifacts, deterministic method calculations, and stage readiness for a confirmed multi-question Study run.
tags:
- Research
security:
- ApiKeyAuth: []
/api/v1/studies/{studyId}/research-runs:
post:
parameters:
- in: path
name: studyId
required: true
schema:
type: string
format: uuid
responses:
'200':
description: Study queued with its immutable confirmed response contracts.
content:
application/json:
schema:
type: object
required:
- data
properties:
data:
type: object
properties: {}
'400':
description: Plan is incomplete, unconfirmed, invalid, unavailable, or not executable.
'401':
description: Unauthorized.
'403':
description: Study or draft access denied.
'404':
description: Study or draft not found.
'409':
description: Draft already confirmed for another run, or a Mind in an attached Audience has not finished training (legacy code `PANEL_MINDS_NOT_READY`, with `data.notReady` naming them). Retry once training completes.
'422':
description: Required respondent-visible image, file, or URL could not be read. The Study is not queued and no quota is used.
operationId: runStudyQuestions
summary: Confirm and run a multi-question Study block
description: Execute an exact saved research-plan revision after explicit confirmation, including every confirmed per-question response and attachment contract. The server, not the client or model, marks required capabilities reviewed and enforces advanced-method opt-in, method availability, and durable media resolution.
tags:
- Research
security:
- ApiKeyAuth: []
requestBody:
required: true
content:
application/json:
schema:
type: object
required:
- draftPlanId
- revision
- confirmation
properties:
draftPlanId:
type: string
format: uuid
revision:
type: integer
minimum: 1
confirmation:
type: object
required:
- accepted
properties:
accepted:
type: boolean
enum:
- true
advancedMethodOptIn:
type: boolean
audienceIds:
type: array
items:
type: string
format: uuid
idempotencyKey:
type: string
format: uuid
modelConnection:
type: object
additionalProperties: false
required:
- id
- revision
properties:
id:
type: string
format: uuid
revision:
type: integer
minimum: 1
description: Verified caller-team connection for Mind answers and verbatim rendering. Pinned at confirmation; retries must keep the same selection. Supporting analysis retains platform models.
/api/v1/studies/{studyId}/summary:
get:
parameters:
- in: path
name: studyId
required: true
schema:
type: string
format: uuid
responses:
'200':
description: Persisted semantic summary.
content:
application/json:
schema:
type: object
required:
- data
properties:
data:
type: object
'400':
description: Study is not in study mode.
'401':
description: Unauthorized.
'403':
description: Study access denied.
'404':
description: Study not found.
operationId: getStudySemanticSummary
summary: Get a study semantic summary
description: Return the persisted whole-study summary, semantic output blocks, staleness, and message coverage. Renderers are hints; consumers may introduce new UI logic without changing evidence contracts.
tags:
- Research
security:
- ApiKeyAuth: []
post:
parameters:
- in: path
name: studyId
required: true
schema:
type: string
format: uuid
responses:
'200':
description: Generated semantic summary.
content:
application/json:
schema:
type: object
required:
- data
properties:
data:
type: object
'400':
description: Study is not in study mode, or does not have enough content.
'401':
description: Unauthorized.
'403':
description: Study access denied.
'404':
description: Study not found.
operationId: refreshStudySemanticSummary
summary: Generate or refresh a study semantic summary
description: Generate and persist a whole-study summary with flexible semantic blocks. Visual-source evidence is represented as heatmaps rather than generic distribution charts.
tags:
- Research
security:
- ApiKeyAuth: []
components:
securitySchemes:
ApiKeyAuth:
type: http
scheme: bearer
bearerFormat: API Key
description: 'Personal API key. Format: `Bearer minds_…_key`. Create one at https://getminds.ai/settings/api-keys.'