{
  "markdown": "# Rapidly MCP\n\n## Test the idea before you build it\n\nRapidly works inside your AI agent. Bring an idea you already have, or ask it to generate one from a company website. In about five minutes, you get a build prompt for the smallest Pretotyping experiment worth running.\n\nRapidly builds the Lean Canvas, turns the riskiest assumption into a measurable hypothesis, researches a pass mark and designs practical experiments. Your agent builds the test. Real customers give you the evidence.\n\nRapidly MCP is generally available.\n\n[Version 2.0.0](RELEASE-NOTES-2.0.0.md) is published in the [official MCP Registry](https://registry.modelcontextprotocol.io/v0.1/servers/co.rapidly%2Frapidly/versions/2.0.0).\n\nWorks with Claude, Codex, ChatGPT and Hermes. OpenClaw, Grokbot and other agents can also use Rapidly if they support remote MCP.\n\n[Connect Rapidly](https://www.rapidly.co/rapidly-mcp) · [Let your agent set it up](docs/for-agents.md) · [Manual setup](docs/quickstart.md)\n\n## Here's what a first run looks like\n\n> A suburban independent bookshop wants to grow weekday foot traffic and build a younger, regular customer base.\n\nRapidly generated three ideas. We chose the Third-Place Pass: a $19 monthly membership with a guaranteed two-hour weekday seat, a rotating perk and a members' shelf.\n\nRapidly built the Lean Canvas, turned the riskiest demand assumption into a measurable hypothesis and proposed five Pretotyping experiments. The simplest started with staff asking warm, local customers to pay. The next used a counter card and landing page, with a proposed pass mark of 15%.\n\n![The Third-Place Pass landing page built from Rapidly's recommended Fake Door experiment.](docs/assets/third-place-pass-landing.png)\n\n[See the complete Rapidly run](https://www.exponentially.com/experiments/rapidly-mcp/) · [Open the customer-facing landing page](https://www.exponentially.com/experiments/rapidly-mcp/pretotypes/third-place-pass/)\n\nThis was a demonstration for a hypothetical bookshop. The pass mark was a proposal to test, not a measured result. No customer results are claimed.\n\n## Why can't I just ask Claude or Codex?\n\nYou can. We do. The answer will probably look reasonable.\n\nRapidly is useful because the method is already there. For one idea, the core run:\n\n1. saves the idea and builds its full Lean Canvas;\n2. turns the riskiest assumption into a measurable hypothesis and researches the pass threshold;\n3. saves three to five complete experiment options, recommends the easiest credible first test and generates one build prompt for that recommendation.\n\nYour agent handles that complete run through `test_idea`. The other experiment options stay saved with the idea, ready to use later. [See the seven standard tools and three advanced method tools](docs/tools.md).\n\nSuccessful work is also saved with the idea in your Rapidly team instead of disappearing in a chat thread. You can bring the result back later and decide whether to fund it, fix it, stop it or run another test.\n\nThe method combines Alberto Savoia's Pretotyping with our own practice through [4,000+ experiments with client teams](https://www.exponentially.com/) and 200+ workshops.\n\n## Connect Rapidly\n\n### If you're new to Rapidly\n\nOpen [rapidly.co/rapidly-mcp](https://www.rapidly.co/rapidly-mcp) and enter your name, email and team name. Rapidly creates the account and team, then shows your personal token once.\n\nThe page gives you copy-ready setup for Codex CLI and Claude Code. Follow the steps, start a fresh conversation and you're ready to try an idea.\n\n### If you already use Rapidly\n\nConnect with OAuth, choose your Rapidly team and approve access. You don't need to create another account or personal token.\n\nThe exact steps differ between Codex, Claude and ChatGPT. Use the [setup instructions](docs/quickstart.md) for your agent.\n\n### If you're using another agent\n\nGive your agent this address and ask it to connect Rapidly:\n\n```text\nhttps://www.rapidly.co/mcp\n```\n\nUse OAuth if the agent supports it. Otherwise, follow the [agent setup instructions](docs/for-agents.md) to keep your personal token out of chat and project files.\n\n## Start with an idea\n\nTo generate three ideas and fully test all three in one request:\n\n```text\nAsk Rapidly for three ideas for [company], focused on [opportunity], and fully test all three in one go.\n```\n\nRapidly should save all three ideas, complete each Canvas and hypothesis, save three to five experiment options for each idea, and return one build prompt for each recommended first test.\n\nUse one you already have:\n\n```text\nAsk Rapidly to test this idea: [describe the customer, problem and proposed change].\n```\n\nOr ask Rapidly to generate one from a company and its website:\n\n```text\nAsk Rapidly to generate [one or more] ideas for [company name] using [website URL]. Focus on [optional customer, problem or opportunity].\n```\n\nRapidly researches the company, returns grounded ideas with sources and offers to take one through the method. If you're bringing your own idea, add anything you already know, where that information came from and any constraints that matter.\n\nRapidly works through the method one saved stage at a time. Your agent should continue the same `test_idea` automatically while Rapidly reports that work is still in progress. Keep the returned project link; if the conversation stops, include that link or project ID when asking Rapidly to continue. You don't need to choose stages, decide whether to save or manage a retry key.\n\nBy the end, you should have:\n\n- sources you can open and facts you can review;\n- a full Lean Canvas;\n- a measurable hypothesis and decision rule suited to the idea's riskiest assumption;\n- three to five saved experiment options, GO and NO-GO rules, and a recommended first experiment;\n- one build prompt for the recommended test asset.\n\nReview the output, ask your agent to build the asset, then put the test in front of real customers.\n\n[See more example prompts](docs/examples.md)\n\n## Help us improve Rapidly MCP\n\nWe're looking for the points where this becomes confusing or stops being useful.\n\nAfter your run, please tell us:\n\n- Did the connection work the first time?\n- Where did you hesitate or get stuck?\n- Was the proposed experiment small enough to run?\n- What did you keep, and did it change what you planned to do next?\n\nEmail [hello@rapidly.co](mailto:hello@rapidly.co) with the subject `Rapidly MCP feedback`. Tell us which agent you used and where you stopped. We won't share your idea, feedback or results publicly without asking you first. Please remove tokens and customer data from feedback, logs and screenshots.\n\n## Current limits\n\n- A trial includes five new ideas. Taking one idea through its Canvas, hypothesis and experiments still counts as one idea.\n- Paid plans include ten ideas per paid seat per calendar month.\n- Need more? Email [hello@rapidly.co](mailto:hello@rapidly.co) to discuss the right next step for your team.\n- Generated facts, cited sources and proposed targets need human review before use.\n\n## Guides\n\n- [Setup instructions](docs/quickstart.md)\n- [Example prompts](docs/examples.md)\n- [Troubleshooting](docs/troubleshooting.md)\n- [Security and privacy](docs/security-and-privacy.md)\n- [Support](SUPPORT.md)\n- [Security reports](SECURITY.md)\n",
  "bytes": 7274,
  "sha": "fffb44c898f2d6475847962def3aa5968b9ba94393c1f82ec5de487bd9a10354",
  "repo_slug": "exponentially-platform/rapidly-mcp",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_co_rapidly_rapidly_7f22bfc8/readme"
}