Integración MCP

El servidor anuncia actualmente 40 herramientas y mantiene 70 herramientas canónicas invocables, según los datos del servidor en vivo. La respuesta tools/list del servidor conectado es la referencia.

Minds ofrece un servidor Model Context Protocol (MCP) que permite a los asistentes de IA crear studyes de investigación sintética, lanzar encuestas multiperspectiva e interactuar con AI Minds directamente. Esto permite la integración con ChatGPT, Claude, Codex, Gemini CLI, Cursor, VS Code y otros clientes compatibles con MCP.

¿Qué es MCP?

El Model Context Protocol (MCP) es un estándar abierto que permite a los asistentes de IA conectarse de forma segura a herramientas externas y fuentes de datos. Con nuestra integración MCP puedes:

Crear y gestionar AI Minds (expertos, personas, gemelos digitales)
Construir studyes de investigación con audiences de expertos de dominio
Lanzar preguntas tipo encuesta a través de múltiples perspectivas
Obtener analítica estadística sobre las respuestas del study
Exportar informes PDF con marca, resúmenes en markdown o datos en bruto
Organizar Minds en audiences reutilizables

URL del servidor MCP

https://getminds.ai/mcp

Para instrucciones por cliente, consulta la guía de configuración de Minds MCP. Todas las herramientas canónicas y la superficie anunciada en vivo están en la referencia de herramientas de Minds MCP. Quienes desarrollen agentes deben leer también la guía operativa MCP para agentes.

Autenticación

El servidor MCP admite dos métodos de autenticación:

OAuth 2.1 (recomendado) — Los clientes como ChatGPT, Claude, Codex y Gemini CLI lo gestionan automáticamente. Se te pedirá que inicies sesión en tu cuenta de Minds al conectarte. La guía de configuración enumera los permisos que solicita un cliente.
API Key — Para acceso programático, genera una key en Settings → API Keys (empieza por minds_). Pásala como Authorization: Bearer minds_your_key.

Clientes compatibles

Cliente	Widget	Auth	Configuración
ChatGPT	Según el cliente	OAuth	Web: Plugins → Add → Create MCP App, o Minds desde el directorio de plugins; app de escritorio: Plugins → Add → Add MCP server (Streamable HTTP, luego Save → Restart → Authenticate)
Claude (claude.ai y Claude Desktop)	Según el cliente	OAuth	Customize → Connectors → + → Add custom connector
Claude Code	No	OAuth o API key	`claude mcp add --transport http minds https://getminds.ai/mcp`, luego `/mcp` → Authenticate
Codex	No	OAuth o API key	`codex mcp add minds --url https://getminds.ai/mcp`, luego `codex mcp login minds`
Gemini CLI	No	OAuth	Entrada `httpUrl` en `~/.gemini/settings.json`
Cursor	Según el cliente	OAuth	Entrada `url` en `~/.cursor/mcp.json`
VS Code (GitHub Copilot)	Según el cliente	OAuth	MCP: Add Server → HTTP, luego la URL del servidor
Langdock	No	OAuth	Integrations → Add MCP
Windsurf	No	OAuth o API key	Cascade … → Open MCP config file, luego una entrada `serverUrl`

Todos los clientes ven las mismas herramientas anunciadas. Las instrucciones paso a paso para cada cliente están en la guía de configuración; la guía de ChatGPT recorre cada pantalla de ChatGPT.

Todos los clientes reciben enlaces clicables para abrir los resultados en la webapp de Minds, independientemente de si soportan widgets.

Herramientas anunciadas y herramientas canónicas

tools/list devuelve 40 herramientas seleccionadas para la investigación interactiva habitual. En total, el servidor mantiene 70 herramientas canónicas invocables, incluidas herramientas de ciclo de vida que no anuncia. Las integraciones explícitas pueden llamarlas por su nombre canónico cuando el cliente admite llamadas configuradas o directas. Esta separación mantiene enfocada la superficie predeterminada del modelo y conserva el contrato completo de capacidades.

Los alias de herramientas pueden seguir siendo invocables por compatibilidad, pero los agentes deben usar siempre los nombres canónicos de la referencia de herramientas.

Área	Herramienta	Descripción	Comportamiento
Audiences	`list_audiences`	List Audiences. Lists the authenticated user's Audiences, most recently updated first, one page at a time (limit, default 20, and offset; nextOffset continues), with Mind counts, sharing state, and links. includeMinds adds each Audience's member Minds. searchQuery filters by name (case-insensitive, all matches, paged). Each Audience's workspaceUrl is the authenticated workspace link, valid verbatim; sharedAudienceUrl, when present, is the public share link for recipients. addOnRequired marks a paid Marketplace Audience the user has not subscribed to: prefer the user's own Audiences, and only use it after the user subscribes.	Solo lectura
	`import_audience_sources`	Import Audience Research Sources. Imports supplied UTF-8 text, Markdown, CSV and JSON research files into account-owned storage. Accepts file contents rather than local paths. Identical file imports are safe to retry. Optional caller-reviewed grounding JSON binds distributions to existingFiles followed by files in sourceIdx order, returning a normalized snapshot and checksum for audience preview and creation. This operation creates no Audience or Minds and performs no web search or independent verification of supplied percentages.	Escribe
	`create_audience_from_brief`	Create a Grounded Audience from a Brief. Researches a free-text population brief and builds a new Audience of Minds with explicit profiles and exact segment allocation. A new brief returns an evidence-backed draft for review; draft.rework or the displayed review revises that draft before confirmation, and creation requires the user-accepted draft or quota snapshot and its checksum. Every new brief starts a separate draft and, once confirmed, a separate Audience. An Audience that already exists is changed in place by recalibrating it by its id, never rebuilt from a new brief. Supports reviewed respondent datasets. Creation is asynchronous and returns an operation ID. Audiences are private unless link sharing is enabled.	Escribe
	`get_audience_creation_progress`	Audience creation progress. Reads progress and never starts or retries anything: an Audience creation by operationId, with its members’ training; or an existing Audience by audienceId, with its member training and background research, or with recalibrationId one recalibration’s status, retained result or terminal error.	Solo lectura
	`render_audience_review`	Show Audience Creation. Shows source research, distributions, proposed Minds, the draft and training for one or more Audience operations, display only: the user confirms or asks for changes in chat. Multiple operations appear in independent tabs within one widget.	Solo lectura
	`get_audience_limits`	Get Audience Limits. Returns the Audience size ceilings for the authenticated account before an Audience is created: the per-Audience plan cap (including any team allowance), the custom-size maximum and the per-mode ceilings. Relevant whenever a size is named, "as many as possible" is asked for, or a creation mode is chosen.	Solo lectura
	`ask_audience`	Ask One Standalone Audience Question. Asks exactly one standalone question of one existing Audience. It creates a private Study for that Audience, starts asynchronous answers from its Minds, and returns the Study identifier and its links.	Escribe
	`export_audience`	Export Audience Brief. Exports an Audience brief, or with kind "validation_report" the report of its validations (overall score calculation, every KPI, per-question answer shares, provenance), through the same renderer used by the web app. Brief: Markdown, PDF, DOCX, PPTX. Validation report: Markdown, PDF, DOCX, XLSX. Binary artifacts are returned as base64.	Escribe
	`duplicate_audience`	Duplicate Audience. Copy an Audience with independent copies of its Minds and all they know.	Escribe
	`recalibrate_audience`	Change an Existing Audience. Changes an existing Audience in place: it keeps its id, its Minds keep theirs (except copies below), and no Mind is deleted. Covers composition and trait edits, a population pivot, adding members, an exact chart selection (`distributions`), new sources and going deeper (`deepen`), and re-runs its research grounding. Owner, or verified Minds staff with existing direct Audience admin collaboration or an active owner-issued support grant. Staff support is limited to composition amendments: no growth, new sources, Go deeper or shared-Mind waiver. Asynchronous: the result is an accepted operation with its id, not a completed change. Queues behind another edit of the Audience and waits for a Study run on its members. Members shared with other Audiences are replaced here by copies with new ids. Reusing requestKey with identical input retries safely.	Destructiva
	`manage_audience_support`	Manage Audience Support Access. Manage owner-issued, expiring staff access to one Audience’s composition and receipts. Staff cannot self-grant. Revocation stops new work at checkpoints; completed changes remain. No membership, growth, deletion or billing changes.	Destructiva
	`attach_study_audiences`	Attach Audiences to Study. Adds existing accessible Audiences without removing others, planning or starting research. Returns attached and alreadyAttached IDs; retries are safe. With link sharing on, the Audiences and their Minds become publicly readable. Access and plan eligibility are validated first.	Escribe
Studies	`list_studies`	List Studies. Lists the authenticated user's Studies, most recently updated first, one page at a time: limit (default 20) and offset, with nextOffset to continue. Each row carries the Study's Audiences with their Mind counts, stored message count, sharing state and links. searchQuery filters by name (case-insensitive, all matches, paged). Minds and per-question results come from the Study status.	Solo lectura
	`create_study`	Create a Study. Creates a Study workspace from existing Audiences or inline Audience configurations. It does not ask questions or run research, and follow-up research inside an existing Study needs no new Study.	Escribe
	`ask_study`	Ask One Standalone Question in a Study. Submits exactly one respondent-visible question in an existing Study: one standalone question, or one adaptive follow-up whose wording could not be known before earlier results.	Escribe
	`get_study_status`	Get Study Status. Returns Study progress, per-Audience results, original Mind responses, links and export status. In-flight questions report zero Minds answered until completion; partial per-Mind progress is not persisted. questionId selects one question; runId selects a confirmed run with question-level counters. Without either, results cover the entire Study. Values and labels are written in the Study display locale, returned as locale: the language of its confirmed plan, else the stored Study locale, else English.	Solo lectura
	`render_study_results`	Show Final Study Results. Shows the results of finished questions (summary, key findings, Audience breakdowns, Mind responses): one question, or a run's finished questions while the rest still run. Use it whenever the user asks about results. Requires exactly one of questionId or runId.	Solo lectura
	`export_study`	Export Study Results. Starts an asynchronous export of Study results and returns an export job ID. Supports executive briefs and full reports in PDF, DOCX, PPTX, or Markdown, plus raw data in CSV, XLS, or SPSS SAV.	Escribe
	`duplicate_study`	Duplicate Study. Copy a Study with all its questions and results over the same Audiences.	Escribe
	`export_heatmap`	Export Website Heatmap. Exports a completed website heatmap from a Study result, identified by the message ID reported with the completed result. Returns the same ZIP archive as the web app, including its unified-renderer PDF report, Markdown, images, and metadata.	Escribe
	`get_study_heatmap`	Read Study Asset Heatmap. Reads saved heatmaps of an assigned question asset. Optional assetKey selects its saved upload path or normalized URL. Returns assetHeatmaps without starting analysis, spending responses or visiting websites.	Solo lectura
	`start_study_heatmap`	Start Study Asset Heatmap. Starts attention analysis of an assigned image, video or website. Uses one response per Mind and needs a paid plan. assetKey reuses completed analysis of that asset; omitting it may replace earlier derived results. Websites are visited publicly. Explicit approval is required; question answers are preserved.	Destructiva
	`create_study_plan`	Create Study Plan. Creates a non-executing draft in an existing Study with its Audiences already attached. The setup operation for two or more known questions: every question known now belongs in this one draft, in cohesive named modules. A one-question draft is only for genuinely standalone research or an adaptive follow-up. request designs questions; questions preserves a fixed instrument verbatim. Each Mind sees only its own earlier answers; askIf applies respondent-level skip logic. With multiple attachments, stimulus.questionAttachments assigns each question; [] means none. Saving bounded history may prune older revisions. Research has not started; the returned draft revision needs review and later explicit confirmation.	Destructiva
	`revise_study_plan`	Revise Study Plan. Revises one saved draft at its current draft.id and draft.revision without starting research. Accepts edits, refinement, clarification answers or response-format corrections. Stale revisions fail. Fixed questions stay verbatim when only clarification answers change. Bounded history may prune older revisions; the changed draft requires review again.	Destructiva
	`get_study_plan`	Read Study Plan. Reads the latest saved revision and full review of one draft. Creates or changes nothing and starts no research.	Solo lectura
	`render_study_plan`	Show Study Plan. Shows a saved Study draft at its current revision for interactive review and confirmation. Research has not started.	Solo lectura
	`read_study_summary`	Read Study Summary. Reads saved whole-Study Markdown, evidence blocks and metadata. Does not regenerate or replace the summary.	Solo lectura
	`refresh_study_summary`	Refresh Study Summary. Generates and saves a whole-Study summary after explicit approval. Replaces the prior summary without restore history; answers and questions are preserved. force regenerates unchanged coverage. Returns Markdown and evidence blocks.	Destructiva
Planificación de investigación	`start_study_run`	Start Confirmed Study Run. Runs one reviewed draft revision after explicit confirmation in a later user turn; skipping review is not confirmation. One execution submits the whole draft as a single durable run. It is refused as a whole before using Minds or quota if the revision, capabilities, method or source-readability checks fail. Advanced methods need explicit opt-in. Each Mind answers in order seeing its own earlier answers; askIf gates items. Contradictions are flagged, never rewritten.	Escribe
	`resume_study_run`	Resume Study Run. Resumes an existing plan-limited Study run in place after explicit user approval and the required paid-plan entitlement. Keeps the originally confirmed questions and response contracts and does not ask questions already answered. Does not start a new draft or change the run design.	Escribe
	`list_research_methods`	List Research Methods. Reads the fixed Minds research-method catalog in one operation, including availability, complexity and fallback method. includePlanned only filters the returned catalog. It does not create, configure or execute a method, and the catalog cannot be edited through this tool.	Solo lectura
Plantillas y borradores	`list_study_drafts`	List Study Drafts. Lists a page of unfinished Study draft summaries, newest first, or returns the complete saved planning state for one exact draft ID. Draft records are distinct from running or completed studies.	Solo lectura
	`list_study_templates`	List Study Templates. Lists your own and team-shared Study templates, most used first, as a page of summaries (templateId, name, revision, method, question count), or returns one exact templateId with its revision, research method, questions, response settings and question attachments. configuration.questions is a fixed, pre-registered instrument and configuration.methodId the research method it runs with; both can be planned as they are.	Solo lectura
	`save_study_draft`	Save Study Draft. Creates or checkpoints an unfinished Quick or Custom Study draft without starting research. It saves the objective, context, selected Audiences, method, questions, sources, and current planner step. Revisions change only the fields given and require the exact draft ID and expected revision; stale writes are rejected. For a retryable creation, choose idempotencyKey before the first save and reuse it after an uncertain result.	Destructiva
	`save_study_template`	Save Study Template. Creates a private Custom template with its questions, response settings, attachments and method. template.requestId enables safe retries. Does not change existing templates, create a draft or start research.	Escribe
	`update_study_template`	Update Study Template. Updates one owned Custom template at update.expectedRevision. Replaces supplied fields without restore history and may share it with the team. Requires explicit approval; stale revisions fail. Does not start research.	Destructiva
	`use_study_template`	Create Draft From Study Template. Creates an independent editable Study draft from a readable template at use.expectedRevision. Reuse use.requestId for retries of the same intended draft. Fresh context and Audiences are added in the web app; the template is unchanged and research does not start.	Escribe
	`delete_study_template`	Delete Study Template. Only for saved Study templates; it cannot delete Studies, Audiences, Minds or answers. Permanently deletes one template owned by the authenticated user. Studies and drafts already created from it are unaffected. Teammates with shared access cannot delete a template they do not own.	Destructiva
Minds	`export_mind`	Export Mind Persona Profile. Generates a branded profile for one existing Mind, identified by exact ID or name (partial names and typos resolve to the closest). Markdown is returned inline by default; PDF, DOCX, and PPTX artifacts are returned as base64 with a workspace link.	Escribe
Minds	`get_shared_mind_knowledge`	Read Shared Mind Sources. Read shared Mind sources and assessments.	Solo lectura

Vista previa interactiva

Minds registra actualmente tres vistas MCP: resultados de Studies (para una pregunta nueva y para una Study existente), revisión del plan de investigación y creación de Audiences. Usan componentes Minds UI; el cliente determina el marco y las interacciones.

La vista actual del plan muestra el borrador guardado. Pide cambios en la conversación y confirma expresamente la última revisión antes de ejecutarla. Ver un plan no inicia una Study.

Si el widget detecta un host móvil, muestra un enlace para continuar en Minds. No inicia controles interactivos ni consultas periódicas del widget. Esto afecta a la presentación, no a la disponibilidad de las herramientas MCP. Se siguen aplicando las restricciones del cliente.

Los ejemplos siguientes usan datos ilustrativos. Cada pestaña es una vista, con las herramientas que la abren; los estados de carga y en curso son capturas fijas, no investigación en curso.

3 widgets · 13 estados de vista previa

Explora cada widget MCP

The first render, before the host delivers the question's data.

Datos ilustrativos · el aspecto varía según el cliente

Flujos de trabajo de n8n

Utilice el nodo de la comunidad Minds para n8n para crear Estudios, previsualizar planes de investigación, recuperar Estudios y resúmenes guardados, o exponer una operación a un Agente de IA. Instale n8n-nodes-minds en n8n autohospedado y conecte una clave API de Minds. El paquete está publicado en npm; la verificación de n8n está bajo revisión, por lo que aún no está disponible en n8n Cloud. Revise e inicie la investigación por separado en Minds.