MCP-Integration

Der Server bietet derzeit 50 Tools an und hält 77 kanonische Tools aufrufbar; beide Werte werden live vom Server gelesen. Maßgeblich ist die Antwort des verbundenen Servers auf tools/list.

Minds stellt einen MCP-Server (Model Context Protocol) bereit, über den KI-Assistenten synthetische Research-Studies erstellen, Multi-Perspektiven-Umfragen durchführen und direkt mit KI-Minds interagieren können. Damit lässt sich Minds in ChatGPT, Claude, Codex, Gemini CLI, Cursor, VS Code und andere MCP-kompatible Clients einbinden.

Was ist MCP?

Das Model Context Protocol (MCP) ist ein offener Standard, mit dem KI-Assistenten sicher auf externe Tools und Datenquellen zugreifen können. Mit unserer MCP-Integration kannst du:

KI-Minds erstellen und verwalten (Expert:innen, Personas, digitale Zwillinge)
Research-Studies mit Audiences von Fachexpert:innen aufbauen
Umfragen an mehreren Perspektiven parallel laufen lassen
Statistische Auswertungen der Study-Antworten abrufen
Gebrandete PDF-Reports, Markdown-Zusammenfassungen oder Rohdaten exportieren
Minds in wiederverwendbare Audiences organisieren

MCP-Server-URL

https://getminds.ai/mcp

Für die Einrichtung nach Client siehe den Minds MCP Setup Guide. Alle kanonischen Tools und die live angebotene Tool-Auswahl stehen in der Minds MCP Tool-Referenz. Wer Agents entwickelt, sollte außerdem den MCP-Leitfaden für Agents lesen.

Authentifizierung

Der MCP-Server unterstützt zwei Authentifizierungsmethoden:

OAuth 2.1 (empfohlen) — Clients wie ChatGPT, Claude, Codex und Gemini CLI übernehmen das automatisch. Beim Verbinden meldest du dich in deinem Minds-Konto an. Welche Berechtigungen ein Client anfordert, steht im Setup Guide.
API Key — Für programmatischen Zugriff: einen Key unter Settings → API Keys erzeugen (beginnt mit minds_). Als Authorization: Bearer minds_your_key mitsenden.

Kompatible Clients

Client	Widget	Auth	Einrichtung
ChatGPT	Clientabhängig	OAuth	Web: Plugins → Add → Create MCP App oder Minds aus dem Plugin-Verzeichnis; Desktop-App: Plugins → Add → Add MCP server (Streamable HTTP, dann Save → Restart → Authenticate)
Claude (claude.ai und Claude Desktop)	Clientabhängig	OAuth	Customize → Connectors → + → Add custom connector
Claude Code	nein	OAuth oder API key	`claude mcp add --transport http minds https://getminds.ai/mcp`, dann `/mcp` → Authenticate
Codex	nein	OAuth oder API key	`codex mcp add minds --url https://getminds.ai/mcp`, dann `codex mcp login minds`
Gemini CLI	nein	OAuth	`httpUrl`-Eintrag in `~/.gemini/settings.json`
Cursor	Clientabhängig	OAuth	`url`-Eintrag in `~/.cursor/mcp.json`
VS Code (GitHub Copilot)	Clientabhängig	OAuth	MCP: Add Server → HTTP, dann die Server-URL
Langdock	nein	OAuth	Integrations → Add MCP
Windsurf	nein	OAuth oder API key	In Cascade … → Open MCP config file, dann ein `serverUrl`-Eintrag

Alle Clients sehen dieselben angebotenen Tools. Schritt-für-Schritt-Anleitungen für jeden Client stehen im Setup Guide; der ChatGPT-Leitfaden führt durch jeden ChatGPT-Bildschirm.

Alle Clients erhalten anklickbare Links, um Ergebnisse in der Minds-Web-App zu öffnen — unabhängig davon, ob Widgets unterstützt werden.

Angebotene und kanonische Tools

tools/list liefert 50 kuratierte Tools für die gewöhnliche interaktive Forschung. Insgesamt hält der Server 77 kanonische Tools aufrufbar, darunter Lebenszyklus-Tools, die er nicht anbietet. Explizite Integrationen können diese Tools über ihren kanonischen Namen aufrufen, sofern der Client konfigurierte oder direkte Tool-Aufrufe unterstützt. Diese Trennung hält die Standard-Tool-Auswahl für das Modell fokussiert und bewahrt zugleich den vollständigen unterstützten Funktionsumfang.

Tool-Aliasse können aus Kompatibilitätsgründen aufrufbar bleiben, Agents sollten aber immer die kanonischen Namen aus der Tool-Referenz verwenden.

Bereich	Tool	Beschreibung	Verhalten
Audiences	`list_audiences`	List Audiences. For a listing or search reply, include both the returned top-level workspaceUrl and each listed Audience's workspaceUrl verbatim in inline code: scheme, query and trailing slash. Item links do not replace the list-level link. Lists owned Audiences newest first with counts and sharing. workspaceUrl opens the owner's workspace; sharedAudienceUrl is public. addOnRequired omits links/commercial details; use an available Audience. First-page openDrafts: rework matching drafts or recalibrate matching Audiences before a new brief.	Nur lesend
	`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.	Schreibend
	`create_audience_from_brief`	Create a Grounded Audience from a Brief. Builds grounded Audience/Mind profiles with exact segment allocation. Returns an asynchronous draft/operation for review; create only after the user accepts its roster/quota snapshot and checksum. Rework the same draft.id/sha256 in place, overwriting its saved request, roster and grounding; never start a new brief for that edit. Supports reviewed datasets and public research/files. Existing Audiences use recalibration. Private unless link sharing is enabled.	Destruktiv
	`get_audience_creation_progress`	Audience creation progress. Read-only; never starts or retries work. operationId: creation and member training. audienceId: training, background research, validation.ready (validation's 10-ready-Mind rule), validation.reason MINDS_TRAINING (poll later) or AUDIENCE_TOO_SMALL (add Minds). recalibrationId: its status, retained result or terminal error. Final score needs all members trained and research done.	Nur lesend
	`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.	Nur lesend
	`get_audience_limits`	Get Audience Limits. Returns the authenticated account's current plan (`planName`, as the app names it), its Audience size allowance (per-Audience cap including any team or contract allowance, `customSizeMax`, per-mode ceilings) and the synthetic responses left, read live; it supersedes limits stated elsewhere. Sample sizes the plan allows: up to `customSizeMax` Minds per Audience, or several Audiences in one Study for a larger sample, each costing one response per Mind per question.	Nur lesend
	`ask_audience`	Ask One Standalone Audience Question. Accepts one standalone question request for an Audience, restricted to supplied segments, and creates a private Study. Returns IDs/links. For preparing, lead with userFacingStatus and call it a request throughout.	Destruktiv
	`export_audience`	Export Audience Brief. Exports an Audience brief or kind validation_report (scores, KPIs, answer shares, provenance) as Markdown/PDF/DOCX/PPTX. Brief PDF/PPTX can fetch public HTTPS member portraits. Starts artifact work; force can replace it. Slow exports may irreversibly email the requesting account.	Destruktiv
	`duplicate_audience`	Duplicate Audience. Adds an independent copy of an Audience, its Minds and retained knowledge. Unready copies can queue retraining with public web research when retained evidence cannot seed them. Ready copies avoid retraining.	Schreibend
	`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.	Destruktiv
	`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.	Destruktiv
	`attach_study_audiences`	Attach Audiences to Study. Attaches existing accessible Audiences without removing others, planning or running research. Optional segmentSelections retain exact matches. Returns attached/alreadyAttached IDs; retries are safe. Link sharing makes these Audiences and Minds public. Validates access and plan eligibility.	Schreibend
Studies	`list_studies`	List Studies. List or search saved Studies, or read an authorized team catalog, result feed or tracker snapshot with source identities, full-filter totals and page continuation.	Nur lesend
	`create_study`	Create a Separate Study Workspace. Creates a separate, new Study workspace when the user requests a new workspace. It can attach existing Audiences or create Audiences inline. It does not ask questions or run research. It does not act in an existing Study or save a draft there.	Schreibend
	`ask_study`	Ask One Standalone Question in a Study. Requests exactly one respondent-visible question: one standalone question, or one adaptive follow-up whose wording could not be known before earlier results. Out of scope: questionnaires, batteries, sections or two or more known questions; use one confirmed block, submitted once rather than question by question. Durably accepts before execution. planning_required requires confirmation. Question text can reach the Minds; exclude planner/client notes. Pasted material: verbatim in evidence.textAttachments. Accepts files shared in the conversation (uploaded or generated images, PDFs). Returns IDs/links. Fixed time-bucket retries can submit again; check status before repeating uncertain writes.	Destruktiv
	`get_study_status`	Get Study Status. Read Study progress, saved replies, uncalibrated forecasts and exports without generating replies. Scope by runId or questionId (including a preparation clientRequestId). A preparing request has userFacingStatus and no submitted question.	Destruktiv
	`request_study_answers`	Request Study Replies. Request actual replies (default 8; all=true for all). May spend response allowance.	Destruktiv
	`render_study_results`	Show Study Results. Completed Study results or labeled experimental, uncalibrated forecasts. Exactly one runId/questionId. Replies load on request. May recover and replace derived results from accepted answers without rerunning Minds.	Destruktiv
	`export_study`	Export Study Results. Queues Study results export: executive/full reports in PDF/DOCX/PPTX/Markdown; raw CSV/XLS/SPSS SAV. Returns job/artifact status. Full reports can fetch public HTTPS portraits. force can replace artifacts. Completed exports can irreversibly email the requesting account.	Destruktiv
	`duplicate_study`	Duplicate Study. Permanently copy a Study with its questions and results over the same Audiences.	Schreibend
	`export_heatmap`	Export Website Heatmap. Exports a completed website heatmap by Study/message ID as a ZIP of stored screenshots and overlays. Does not recapture the website. force starts fresh archive work and replaces its saved artifact status/reference.	Destruktiv
	`get_study_heatmap`	Read Study Asset Heatmap. Read saved attention by assetKey and, for monadic Studies, variantId. No new analysis, website visits, or response charges.	Nur lesend
	`start_study_heatmap`	Start Study Asset Heatmap. Start or retry analysis of an assigned original file, image, video or public website, including a monadic variantId. Mosaic prepares original files internally and retains saved material findings and visual groups. Eligible Mosaic Reactions start automatically with the Study and use no additional response credits. Other paid or legacy analysis requires approval, a paid plan and one response per Mind. Preserves question answers.	Destruktiv
	`create_study_plan`	Draft Research in an Existing Study. Saves a non-executing research draft in an existing Study, including a multi-question concept test or survey. It creates no Study workspace and starts no research. study.name directly resolves the existing Study and its Audiences by name. study.id selects an ID; omission uses the active Study.	Destruktiv
	`revise_study_plan`	Revise Study Plan. Revises the saved draft at current draft.id and draft.revision without starting research. Nest changes in draft.refinement, answers in draft.answers, formats in draft.questionResponses, or exact edits in draft.edits. Replacement questions are top-level questions. Stale revisions fail; answers alone preserve fixed wording. Review the new revision. History is bounded.	Destruktiv
	`get_study_plan`	Read Study Plan. Reads the latest saved revision and full review of one draft. Read-only; starts no research.	Nur lesend
	`render_study_plan`	Show Study Plan. Shows a saved Study draft at its current revision for interactive review and confirmation. Research has not started.	Nur lesend
	`cancel_study_question`	Stop Standalone Study Question. Stops one standalone Study question by runId, or studyId and questionId: queued or preparing stops at once, being answered stops at its next step. Answers given are kept. A delivered forecast keeps its completed run history while remaining replies and Reactions can still be stopped. An answered question with no pending work, or a failed question with no work stopped, errors unchanged. Not for multi-question runs.	Destruktiv
	`read_study_summary`	Read Study Summary. Reads saved whole-Study Markdown, evidence, generation state and your refresh receipt. Pending retains prior content. May recover/replace stale or missing summaries; never reruns respondents.	Destruktiv
	`refresh_study_summary`	Refresh Study Summary. Queues a whole-Study summary refresh after explicit approval. Replaces it without restore history; preserves questions/answers. force regenerates unchanged coverage. Pending returns a receipt and prior content.	Destruktiv
Forschungsplanung	`cancel_study_run`	Cancel Study Run. Stop pending Study work; keep saved replies. Returns run/collection status.	Destruktiv
	`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.	Destruktiv
	`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.	Destruktiv
	`list_research_methods`	List Research Methods. Lists the research-method catalog without changing or running methods. For availability, report every label and the exact count in each availabilitySummary group. Use methods for complexity and fallbacks; advanced methods can require opt-in.	Nur lesend
	`plan_study_questions`	Plan a Multi-Question Block in a Study. Deprecated alias of create_study_plan and revise_study_plan; identical behaviour.	Destruktiv
	`run_study_questions`	Run a Confirmed Multi-Question Block. Deprecated alias of start_study_run; identical behaviour.	Destruktiv
Vorlagen & Entwürfe	`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.	Nur lesend
	`list_study_templates`	List Study Templates. Lists owned/team-shared template summaries, most used first; templateId returns full configuration, revision, questions, response settings and attachments. configuration.questions is the fixed instrument; configuration.methodId the research method it runs with. Listing provisions starters or overwrites eligible untouched older starters. Exact-template reads skip provisioning.	Destruktiv
	`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.	Destruktiv
	`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.	Schreibend
	`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.	Destruktiv
	`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.	Schreibend
	`delete_study_template`	Delete Study Template. Only for saved Study templates; it cannot delete Studies, Audiences, Minds or answers. Permanently deletes one template the authenticated user owns; Studies and drafts already created from it are unaffected.	Destruktiv
Minds	`export_mind`	Export Mind Persona Profile. Exports an existing Mind by ID/name: inline Markdown by default, or PDF/DOCX/PPTX. PDF/PPTX can fetch public HTTPS portraits. Starts artifact work; force can replace an artifact. Slow exports may irreversibly email the requesting account when ready.	Destruktiv
Minds	`get_shared_mind_knowledge`	Read Shared Mind Sources. Returns stored public Mind sources/assessments by share ID, including shares outside the private workspace. Does not fetch source websites or modify knowledge.	Nur lesend
Weitere	`list_formations`	List Audience Segmentations. Lists Audience segmentations for filters; may save defaults and recover builds, replacing subgroup memberships. Ready counts are final. Paged (limit 1–100, default 100); follow pagination.nextOffset.	Destruktiv
	`update_item`	Update Study, Audience or Mind. Renames a Study or Audience or moves it into a folder. Renames a Mind, or records whether its facts come from real research data (mind.factsSource).	Destruktiv
	`set_sharing`	Change Study or Audience Sharing. Turns a Study's or Audience's public link or team sharing on or off.	Destruktiv
	`enterprise_use_cases`	Enterprise use cases. Read paged team business use cases and role-scoped counts of attributed drafts, Studies and completed runs.	Nur lesend
	`save_enterprise_use_case`	Save enterprise use case. Save a revision-checked team business use case with objectives, template revisions, planned targets and lifecycle state.	Destruktiv

Interaktive Vorschau

Minds registriert derzeit drei MCP-Ansichten: Study-Ergebnisse (für eine neue Frage und für eine bestehende Study), Forschungsplan-Prüfung und Audience-Erstellung. Sie verwenden Minds-UI-Komponenten. Rahmen und Interaktionen hängen vom Client ab.

Die aktuelle Planansicht zeigt den gespeicherten Entwurf zur Prüfung. Bitte im Gespräch um Änderungen und bestätige die neueste Revision ausdrücklich, bevor der Assistent sie ausführt. Das Anzeigen eines Plans startet keine Study.

Erkennt ein Widget einen mobilen Host, zeigt es einen Link zum Fortsetzen in Minds. Interaktive Bedienelemente und Widget-Polling starten dort nicht. Das betrifft die Darstellung, nicht die Verfügbarkeit der MCP-Tools. Einschränkungen des Clients gelten weiterhin.

Die folgenden Beispiele verwenden illustrative Daten. Jeder Tab zeigt eine Ansicht mit den Tools, die sie öffnen; Lade- und Fortschrittsbeispiele sind feste Momentaufnahmen, keine laufende Forschung.

3 Widgets · 13 Vorschauzustände

Alle MCP-Widgets ansehen

Angezeigt von: render_study_results

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

Beispieldaten · Darstellung variiert je nach Client

n8n-Workflows

Verwenden Sie den Minds-Community-Node für n8n, um Studies zu erstellen, Forschungspläne in der Vorschau anzuzeigen, Studies und gespeicherte Zusammenfassungen abzurufen oder eine Operation für einen AI Agent bereitzustellen. Installieren Sie n8n-nodes-minds auf selbst gehostetem n8n und verbinden Sie einen Minds API-Schlüssel. Das Paket ist auf npm veröffentlicht; die n8n-Verifizierung wird geprüft, daher ist es auf n8n Cloud noch nicht verfügbar. Überprüfen und starten Sie die Forschung separat in Minds.