{
  "markdown": "# Minds MCP Server\n\n[![smithery badge](https://smithery.ai/badge/alexander-a4p3/minds)](https://smithery.ai/servers/alexander-a4p3/minds)\n[![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.21711429.svg)](https://doi.org/10.5281/zenodo.21711429)\n\nRun AI market research from your assistant: build synthetic Audiences and run\nStudies for concept testing, message testing, and segment comparison.\n\n**Endpoint:** `https://getminds.ai/mcp` (streamable HTTP)\n**Docs:** https://getminds.ai/mcp/setup\n**Quick-start guide:** https://minds-ai-co.github.io/minds-mcp/\n**Technical reference:** https://minds-mcp.readthedocs.io/en/latest/\n**GitBook:** https://minds-1.gitbook.io/minds-mcp/\n**Client compatibility:** https://minds-mcp-compatibility.pages.dev/\n**Setup generator:** https://minds-mcp-setup-generator.netlify.app/\n**Public API explorer:** https://minds-api-explorer.vercel.app/?utm_source=content&utm_medium=content&utm_campaign=content-seo-mcp-reference&utm_content=mcp-repository-api-explorer\n**API + MCP integration lab:** https://minds-api-mcp-integration-lab-bba685.gitlab.io/?utm_source=content&utm_medium=content&utm_campaign=content-seo-mcp-reference&utm_content=mcp-repository-integration-lab\n**Archived release:** https://doi.org/10.5281/zenodo.21711429\n**Auth:** OAuth 2.1 with PKCE (dynamic client registration or Client ID Metadata Documents), or a Minds API key (`Authorization: Bearer minds_…`)\n\n> This repository is documentation for a hosted MCP server. There is no code to\n> install or run. The server is operated by [Minds](https://getminds.ai) and the\n> implementation lives in our application, not here.\n\n## Documentation maintenance\n\n`reference/` is the single source for maintained integration content. Read the\nDocs and GitBook publish the same Markdown through repository sync. GitHub Pages,\nCloudflare Pages, and the Netlify setup generator are intentionally thin,\nplatform-specific surfaces; Zenodo preserves versioned release snapshots. See\n[DOCUMENTATION.md](DOCUMENTATION.md) for the publishing contract.\n\n## What it does\n\n[Minds](https://getminds.ai) is a synthetic market research platform. This MCP\nserver lets ChatGPT, Claude, Cursor, and any other MCP client run customer\nresearch end to end without leaving the assistant.\n\nDescribe an audience in a brief (\"German Gen Z grocery shoppers\", \"enterprise IT\nbuyers in fintech\") and the server runs deep web research to ground that audience\nin government statistics, peer-reviewed studies, and industry reports rather than\nin generic model priors. Then ask the Audience a question, run a structured\nStudy, and export the results.\n\nTypical jobs:\n\n- Concept testing and message testing before creative production\n- Ad pretesting, landing page audits, and packaging tests with per-segment reactions\n- Buyer persona validation and objection discovery for B2B go to market\n- Segment comparison and positioning checks across markets\n- Screening research hypotheses before commissioning fieldwork with real respondents\n\nStudies run durably server side, so a long study survives the chat session that\nstarted it. Results export to PDF, DOCX, PPTX, Markdown, CSV, XLS, and SPSS SAV.\n\n**Scope.** Minds does not replace representative human fieldwork. It replaces the\nslow first pass: sharpening the question, surfacing objections, and deciding which\nassumptions deserve real-respondent validation.\n\n## Setup\n\n### ChatGPT\n\nEnable developer mode under **Settings → Security and login**, then open\n**Plugins** and select the plus button. Add `https://getminds.ai/mcp` as a public\nHTTPS connection, choose OAuth, and sign in to Minds. Availability depends on\nyour account and workspace policy.\n\nStudy results can render as interactive widgets inline. See the\n[official OpenAI connection guide](https://developers.openai.com/plugins/deploy/connect-chatgpt)\nand the [Minds setup guide](https://getminds.ai/guide/integration-chatgpt).\n\n### Claude Desktop and claude.ai\n\nCustomize, then Connectors, then add `https://getminds.ai/mcp` as a remote\nconnector and authorize via OAuth.\n\n### Claude Code\n\n```bash\nclaude mcp add --transport http mindsai https://getminds.ai/mcp \\\n  --header \"Authorization: Bearer minds_YOUR_API_KEY\"\n```\n\n### Cursor\n\nSettings, then MCP, then add `https://getminds.ai/mcp` and authorize via OAuth.\nThe repository also contains a Marketplace-ready Cursor plugin manifest at\n`.cursor-plugin/plugin.json`; its MCP configuration is intentionally kept in\n`cursor.mcp.json` so the shared Agent Plugins configuration can retain the\nportable `streamable-http` transport name.\n\n### Google Antigravity\n\n```bash\nagy plugins install https://github.com/minds-ai-co/minds-mcp\n```\n\nThe root `plugin.json` and `mcp_config.json` make this repository an Antigravity\nplugin. Antigravity discovers OAuth from the hosted endpoint; authenticate under\nSettings, then Customizations. To add only the server, run\n`agy mcp add --type http minds https://getminds.ai/mcp` or put\n`{\"mcpServers\": {\"minds\": {\"serverUrl\": \"https://getminds.ai/mcp\"}}}` in\n`~/.gemini/config/mcp_config.json`. Full guide:\nhttps://getminds.ai/guide/integration-antigravity\n\nGemini CLI remains supported for Google Cloud enterprise and API-key users. Its\nlegacy extension manifest stays available as `gemini-extension.json`.\n\n### ChatGPT and Codex Plugins\n\nThe repository includes the shared plugin package at\n`.codex-plugin/plugin.json` and its remote server configuration in `.mcp.json`.\nThe public directory listing uses the same hosted endpoint and maintained\nreference content.\n\n### VS Code (Copilot), Windsurf, Langdock, Open WebUI\n\nAdd `https://getminds.ai/mcp` as a remote MCP server. Full per-client instructions,\nincluding API key setup, are at https://getminds.ai/mcp/setup.\n\n### API keys\n\nGenerate one in the Minds app under **Settings → API Keys**. Keys start with\n`minds_` and are passed as `Authorization: Bearer minds_...`.\n\n## Tools\n\n<!-- tools:start -->\n<!-- Generated by scripts/sync-mcp-surface.mjs from the production MCP surface. Do not edit by hand. -->\n\nThe server advertises 45 tools. Clients read the current schemas at runtime;\nthe full list with access levels is in [reference/tools.md](reference/tools.md).\n\n| Tool | What it does |\n| --- | --- |\n| `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. |\n| `import_audience_sources` | Imports supplied UTF-8 text, Markdown, CSV and JSON research files into account-owned storage. |\n| `create_audience_from_brief` | Researches a free-text population brief and builds a new Audience of Minds with explicit profiles and exact segment allocation. |\n| `get_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. |\n| `render_audience_review` | 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. |\n| `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. |\n| `ask_audience` | Asks exactly one standalone question of one existing Audience. |\n| `export_audience` | 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. |\n| `duplicate_audience` | Permanently copy an Audience with independent copies of its Minds and all they know. |\n| `recalibrate_audience` | Changes an existing Audience in place: it keeps its id, its Minds keep theirs (except copies below), and no Mind is deleted. |\n| `manage_audience_support` | Manage owner-issued, expiring staff access to one Audience’s composition and receipts. |\n| `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. |\n| `create_study` | Creates a Study workspace from existing Audiences or inline Audience configurations. |\n| `ask_study` | Submits exactly one respondent-visible question: one standalone question, or one adaptive follow-up whose wording could not be known before earlier results. |\n| `get_study_status` | Returns Study progress, per-Audience results, original Mind responses, links and export status. |\n| `render_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. |\n| `export_study` | Starts an asynchronous export of Study results and returns an export job ID. |\n| `duplicate_study` | Permanently copy a Study with its questions and results over the same Audiences. |\n| `export_heatmap` | Exports a completed website heatmap from a Study result, identified by the message ID reported with the completed result. |\n| `get_study_heatmap` | Reads saved heatmaps of an assigned question asset. |\n| `start_study_heatmap` | Starts attention analysis of an assigned image, video or website. |\n| `export_mind` | Generates a branded profile for one existing Mind, identified by exact ID or name (partial names and typos resolve to the closest). |\n| `get_shared_mind_knowledge` | Read shared Mind sources and assessments. |\n| `create_study_plan` | Creates a non-executing draft in an existing Study with its Audiences already attached. |\n| `revise_study_plan` | Revises one saved draft at its current draft.id and draft.revision without starting research. |\n| `get_study_plan` | Reads the latest saved revision and full review of one draft. |\n| `attach_study_audiences` | Adds existing accessible Audiences without removing others, planning or starting research. |\n| `render_study_plan` | Shows a saved Study draft at its current revision for interactive review and confirmation. |\n| `start_study_run` | Runs one reviewed draft revision after explicit confirmation in a later user turn; skipping review is not confirmation. |\n| `resume_study_run` | Resumes an existing plan-limited Study run in place after explicit user approval and the required paid-plan entitlement. |\n| `cancel_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. |\n| `update_item` | Renames a Study or Audience or moves it into a folder. |\n| `set_sharing` | Turns a Study's or Audience's public link or team sharing on or off. |\n| `list_research_methods` | Reads the fixed Minds research-method catalog in one operation, including availability, complexity and fallback method. |\n| `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. |\n| `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. |\n| `save_study_draft` | Creates or checkpoints an unfinished Quick or Custom Study draft without starting research. |\n| `save_study_template` | Creates a private Custom template with its questions, response settings, attachments and method. |\n| `update_study_template` | Updates one owned Custom template at update.expectedRevision. |\n| `use_study_template` | Creates an independent editable Study draft from a readable template at use.expectedRevision. |\n| `delete_study_template` | Only for saved Study templates; it cannot delete Studies, Audiences, Minds or answers. |\n| `read_study_summary` | Reads saved whole-Study Markdown, evidence blocks and metadata. |\n| `refresh_study_summary` | Generates and saves a whole-Study summary after explicit approval. |\n| `plan_study_questions` | Deprecated alias of create_study_plan and revise_study_plan; identical behaviour. |\n| `run_study_questions` | Deprecated alias of start_study_run; identical behaviour. |\n\nServer card: `https://getminds.ai/.well-known/mcp/server-card.json` (`minds-ai`).\n<!-- tools:end -->\n\nCall `list_research_methods` for current executable status, requirements, and\nfallbacks before choosing a research method.\n\n## Discovery\n\n- Server card: `https://getminds.ai/.well-known/mcp/server-card.json`\n- OAuth protected resource metadata: `https://getminds.ai/.well-known/oauth-protected-resource/mcp`\n- Registry name: `ai.getminds/minds`\n\n## Links\n\n- Product: https://getminds.ai\n- MCP setup guide: https://getminds.ai/mcp/setup\n- API docs: https://getminds.ai/api\n- Versioned integration reference: https://doi.org/10.5281/zenodo.21711429\n- Documentation publishing model: DOCUMENTATION.md\n- GitBook reference: https://minds-1.gitbook.io/minds-mcp/\n- Client compatibility: https://minds-mcp-compatibility.pages.dev/\n- MCP setup generator: https://minds-mcp-setup-generator.netlify.app/\n- Public API explorer: https://minds-api-explorer.vercel.app/?utm_source=content&utm_medium=content&utm_campaign=content-seo-mcp-reference&utm_content=mcp-repository-links-api-explorer\n- API + MCP integration lab: https://minds-api-mcp-integration-lab-bba685.gitlab.io/?utm_source=content&utm_medium=content&utm_campaign=content-seo-mcp-reference&utm_content=mcp-repository-links-integration-lab\n- Support: https://getminds.ai\n- Developer portal distribution model: DISTRIBUTION.md\n- Google Antigravity plugin manifest: plugin.json\n- Google Antigravity MCP configuration: mcp_config.json\n",
  "bytes": 14039,
  "sha": "392c5997174aacf73c0c14250d64639f4ea2238022bc9c2d4b62b5d6f94f111e",
  "repo_slug": "minds-ai-co/minds-mcp",
  "fonte": "repo",
  "truncated": false,
  "api": "https://api.agentalog.com/api/listings/mcp_ai_getminds_minds_7f37a836/readme"
}