{
  "markdown": "# Mimiq MCP Server\n\nYour AI coding agent tests pages, copy, and flows on simulated users — automatically, while you build. Spots bad copy, confusing UX, and conversion killers before real users do.\n\n[![Install in VS Code](https://img.shields.io/badge/VS_Code-Install_MCP-0098FF?style=flat-square&logo=visualstudiocode&logoColor=white)](https://insiders.vscode.dev/redirect?url=vscode%3Amcp%2Finstall%3F%257B%2522name%2522%253A%2522mimiq%2522%252C%2522type%2522%253A%2522http%2522%252C%2522url%2522%253A%2522https%253A%252F%252Fmcp.mimiqai.com%252Fmcp%2522%257D) [![Install in Cursor](https://img.shields.io/badge/Cursor-Install_MCP-black?style=flat-square&logo=cursor&logoColor=white)](https://cursor.com/install-mcp?name=mimiq&config=eyJ0cmFuc3BvcnQiOiJzdHJlYW1hYmxlX2h0dHAiLCJ1cmwiOiJodHRwczovL21jcC5taW1pcWFpLmNvbS9tY3AifQ==)\n\n## Setup (30 seconds)\n\n### Claude Code\n\n```bash\nclaude mcp add --transport http mimiq https://mcp.mimiqai.com/mcp\n```\n\nOr add to `.mcp.json` in your project root:\n\n```json\n{\n  \"mcpServers\": {\n    \"mimiq\": {\n      \"type\": \"http\",\n      \"url\": \"https://mcp.mimiqai.com/mcp\"\n    }\n  }\n}\n```\n\n### Codex\n\nAdd to `~/.codex/config.toml` (or `.codex/config.toml` in your project root):\n\n```toml\n[mcp_servers.mimiq]\nurl = \"https://mcp.mimiqai.com/mcp\"\n```\n\nWith an API key, set the env var and reference it:\n\n```toml\n[mcp_servers.mimiq]\nurl = \"https://mcp.mimiqai.com/mcp\"\nbearer_token_env_var = \"MIMIQ_API_KEY\"\n```\n\nThen set the env var: `export MIMIQ_API_KEY=mq_sk_your_key_here`\n\n### Cursor\n\nAdd to MCP settings (Settings > MCP):\n\n```json\n{\n  \"mimiq\": {\n    \"transport\": \"streamable_http\",\n    \"url\": \"https://mcp.mimiqai.com/mcp\"\n  }\n}\n```\n\n### VS Code (GitHub Copilot)\n\nOpen Command Palette > \"MCP: Add Server\" or add to `.vscode/mcp.json`:\n\n```json\n{\n  \"servers\": {\n    \"mimiq\": {\n      \"type\": \"http\",\n      \"url\": \"https://mcp.mimiqai.com/mcp\"\n    }\n  }\n}\n```\n\n### Windsurf\n\nAdd to `~/.codeium/windsurf/mcp_config.json`:\n\n```json\n{\n  \"mcpServers\": {\n    \"mimiq\": {\n      \"serverUrl\": \"https://mcp.mimiqai.com/mcp\"\n    }\n  }\n}\n```\n\n### Claude Desktop\n\nAdd to your Claude Desktop config:\n\n```json\n{\n  \"mcpServers\": {\n    \"mimiq\": {\n      \"transport\": \"streamable_http\",\n      \"url\": \"https://mcp.mimiqai.com/mcp\"\n    }\n  }\n}\n```\n\n---\n\nNo API key needed — you get **100 free personas** to start.\n\n## Use it\n\nYour agent now has access to Mimiq tools. It uses them **proactively** — when it builds or changes a page, it tests automatically. No need to ask.\n\nIt also works with **localhost**. The agent starts a temporary cloudflared tunnel, runs the simulation, and tears it down. You build, it tests, in the same flow.\n\nOr ask directly:\n\n> \"Test my landing page on startup founders\"\n>\n> \"A/B test these two headlines on e-commerce shoppers\"\n>\n> \"Ask 20 SaaS founders which pricing model they prefer\"\n\n## Tools\n\n| Tool | What it does |\n|------|-------------|\n| `mimiq.test_page` | Test a web page — finds UX issues, confusing copy, conversion blockers |\n| `mimiq.test_flow` | Deep interactive simulation of multi-step flows (signup, checkout) |\n| `mimiq.test_copy` | Test copy or A/B compare two variants head-to-head |\n| `mimiq.test_text` | Test any text content (positioning, descriptions, error messages) |\n| `mimiq.test_component` | Evaluate UI components from HTML snippets |\n| `mimiq.ask_audience` | Survey a synthetic audience on product decisions |\n\n## What you get back\n\nRaw per-persona results. Each simulated user has a name, demographics, and independently decides what to do. You get:\n\n- **action**: what they did (converted, engaged, or bounced)\n- **monologue**: what they were thinking — this is where the real insights are\n- **objections**: specific concerns that stopped them\n- **what_would_help**: what would change their mind\n- **aggregate counts**: how many converted, engaged, or bounced\n\nThere are no pre-computed verdicts or scores. Your AI agent analyzes the raw feedback and decides what it means.\n\n## When you need more\n\nAfter 100 free personas, sign up at [mimiqai.com](https://mimiqai.com) to get an API key (Settings > API Keys), then add it to your config:\n\n**Claude Code:**\n```bash\nclaude mcp remove mimiq\nclaude mcp add --transport http \\\n  --header=\"Authorization: Bearer mq_sk_your_key_here\" \\\n  mimiq https://mcp.mimiqai.com/mcp\n```\n\n**Codex:**\n```toml\n[mcp_servers.mimiq]\nurl = \"https://mcp.mimiqai.com/mcp\"\nbearer_token_env_var = \"MIMIQ_API_KEY\"\n```\nThen: `export MIMIQ_API_KEY=mq_sk_your_key_here`\n\n**Cursor / VS Code / Claude Desktop / Windsurf** — add a `headers` field:\n```json\n{\n  \"headers\": {\n    \"Authorization\": \"Bearer mq_sk_your_key_here\"\n  }\n}\n```\n\n## Pricing\n\n- **100 free personas** on first use (no signup needed)\n- **2,000 personas for $10** at [mimiqai.com/app/usage](https://mimiqai.com/app/usage)\n\n## Self-hosting\n\nIf you're running the Mimiq backend yourself:\n\n```bash\ncd mcp-hosted\nMIMIQ_API_URL=http://127.0.0.1:8000/api node src/server.js\n```\n\nPoint your agent at `http://127.0.0.1:8787/mcp`. In local dev mode, no API key is required.\n\n### Docker\n\n```bash\ncd mcp-hosted\ndocker build -t mimiq-mcp .\ndocker run -p 8787:8787 -e MIMIQ_API_URL=http://host.docker.internal:8000/api -e HOST=0.0.0.0 mimiq-mcp\n```\n\n### Environment variables\n\n| Variable | Default | Description |\n|----------|---------|-------------|\n| `MIMIQ_API_URL` | `http://127.0.0.1:8000/api` | Mimiq backend URL |\n| `MIMIQ_API_KEY` | — | Backend API key (if backend requires shared auth) |\n| `PORT` | `8787` | Server port |\n| `HOST` | `127.0.0.1` | Bind host (`0.0.0.0` for Docker) |\n\n## Testing localhost pages\n\nMimiq works with localhost out of the box. When your agent calls `test_page` or `test_flow` on a local dev server, it automatically:\n\n1. Starts a temporary [cloudflared](https://developers.cloudflare.com/cloudflare-one/connections/connect-apps/run-tunnel/trycloudflare/) tunnel (free, no account needed)\n2. Uses the public tunnel URL for the simulation\n3. Tears down the tunnel when done\n\nThis is the primary workflow — test while you build, not after you deploy.\n\n**Requirement:** `cloudflared` must be installed on the machine running the AI agent.\n\n```bash\n# macOS\nbrew install cloudflared\n\n# Linux\ncurl -L https://github.com/cloudflare/cloudflared/releases/latest/download/cloudflared-linux-amd64 -o /usr/local/bin/cloudflared && chmod +x /usr/local/bin/cloudflared\n```\n\nThe agent handles the rest. No bridge daemon, no extra config, no manual tunnel setup.\n\n## License\n\nMIT\n",
  "bytes": 6440,
  "sha": "df946d46a4e73e0b1c1733f0977b9e197003fd29d72e443d6af986003900f217",
  "repo_slug": "victorgulchenko/mimiq-mcp",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_victorgulchenko_mimiq_mcp_383a2ad0/readme"
}