{
  "markdown": "# Magic Insights MCP server\n\nConnect any [MCP](https://modelcontextprotocol.io) client to your [Magic Insights](https://magicinsights.ai) workspace and chat with your customer-feedback **studies** — list studies, search and filter feedback, and read AI-generated themes, topics, suggestions, tags, and sentiment trends.\n\nThis is a **remote, hosted** MCP server. There's nothing to install — point your client at the URL below and authenticate with a workspace API key.\n\n- **Server URL:** `https://app.magicinsights.ai/api/mcp`\n- **Transport:** Streamable HTTP\n- **Auth:** API key (bearer token)\n- **Official MCP registry:** [`ai.magicinsights/insights`](https://registry.modelcontextprotocol.io/v0/servers?search=ai.magicinsights)\n\n## Get an API key\n\nCreate one in the app at **Settings → API keys** (`https://app.magicinsights.ai` → your workspace → Settings → API keys), then send it as the `Authorization: Bearer <key>` header.\n\n## Connect\n\n### Claude Code\n\n```bash\nclaude mcp add --transport http magic-insights https://app.magicinsights.ai/api/mcp \\\n  --header \"Authorization: Bearer YOUR_API_KEY\"\n```\n\n### Cursor\n\nAdd to `~/.cursor/mcp.json` (all projects) or `.cursor/mcp.json` (one project), then enable the server in Cursor settings:\n\n```json\n{\n  \"mcpServers\": {\n    \"magic-insights\": {\n      \"url\": \"https://app.magicinsights.ai/api/mcp\",\n      \"headers\": {\n        \"Authorization\": \"Bearer YOUR_API_KEY\"\n      }\n    }\n  }\n}\n```\n\n### Other clients (Claude Desktop, Windsurf, MCP Inspector, …)\n\nMost clients use the same `mcpServers` block above — check your client's docs for where its config file lives. The Claude API MCP connector accepts the same URL with an `authorization_token`.\n\n## Tools\n\nAll tools are **read-only** and scoped to the workspace that owns the API key.\n\n| Tool | What it does |\n| --- | --- |\n| `get_workspace` | One-call overview: plan, study count, connected platforms, tags, total feedback, date range, overall sentiment. |\n| `list_studies` | List all studies with description and date range. |\n| `get_study` | A study's summary, generated report, and top themes (with sentiment, ids, and example feedback). |\n| `list_topics` | A study's topics and the themes grouped under each. |\n| `get_theme_feedback` | All feedback under one theme, most relevant first. |\n| `list_suggestions` | A study's AI-synthesized recommended actions (problem, solution, priority). |\n| `get_suggestion_feedback` | The individual feedback behind a single suggestion. |\n| `search_feedback` | Search and filter feedback by keyword, sentiment, platform, tag, or date range. |\n| `get_feedback` | One feedback item in full — content, translation, AI summary, and source metadata. |\n| `get_stats` | Aggregate stats: total count, sentiment breakdown, date range. |\n| `get_trends` | Feedback volume and sentiment over time, bucketed by week or month. |\n| `list_tags` | The workspace's custom tags and how many items carry each. |\n| `list_platforms` | The source platforms feeding the workspace, each with its feedback count. |\n\n## About\n\nMagic Insights is an AI-driven customer-feedback analytics platform. Learn more at [magicinsights.ai](https://magicinsights.ai).\n\nThe server's metadata is published in the [official MCP registry](https://registry.modelcontextprotocol.io/v0/servers?search=ai.magicinsights); this repository hosts the public `server.json` and connection docs. The application source is closed.\n",
  "bytes": 3417,
  "sha": "047c13c11fcfee528136108ad0c076cf8fef199885a05bc855fa0606e8a9ae23",
  "repo_slug": "andrewchmr/magic-insights-mcp",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_ai_magicinsights_insights_fe32cae3/readme"
}