Rapidly
Test the idea before you build it.
What it can do
- Test Idea: Save or resume one idea and advance it through Canvas, hypothesis, experiment options, recommendation, and a build prompt one durable stage at a time. A completed result returns the full co
- Find Ideas: Generate and save the requested number of ideas from one open brief.
- List Ideas: Page through ideas in the team already authorised by this connection.
What data it sees
Do you need an account
No: the server works without sign-in
Test the idea before you build it. Rapidly works inside your AI agent.
Bring an idea you already have, or ask Rapidly to find one from a company website. Rapidly saves the idea, builds its Lean Canvas and measurable hypothesis, then saves three to five practical Pretotyping experiments.
It recommends the easiest credible first experiment for the riskiest assumption and generates one build prompt for that recommendation. The other experiment options remain saved for later. Your agent builds the test. Real customers provide the evidence.
Start with: Ask Rapidly for three ideas for [company], focused on [opportunity], and fully test all three in one go.
How to connect
How to connect Rapidly to Claude
The server address to paste into Claude settings:
https://rapidly--leslie.run.tools
- Open Claude (claude.ai or the desktop app).
- Go to Settings → Connectors.
- Click Add custom connector.
- Paste the server address copied below into Remote MCP server URL and click Add.
- In a chat, click + → Connectors and switch the new connector on.
Custom connectors are available on Free, Pro, Max, Team and Enterprise plans (Free is limited to one). On Team and Enterprise an organization Owner adds the connector first under Organization settings → Connectors.
Authorization
After you click Add, a sign-in window for the service opens. Sign in with your own account and approve access. Claude never sees your password.
How to connect Rapidly to ChatGPT
The server address to paste into ChatGPT settings:
https://rapidly--leslie.run.tools
- Open ChatGPT in a browser (chatgpt.com). A Plus, Pro, Business, Enterprise or Edu plan is required.
- Turn on developer mode once: Settings → Apps → Advanced settings → Developer mode.
- Open Settings → Connectors and click Create.
- Fill in the form: Name (anything), Description (one line about what the service does), MCP server URL (copy it below).
- Under Authentication choose OAuth if the service requires sign-in, otherwise None. Click Create.
- In a new chat open + → Apps/Connectors and enable the connector.
OpenAI has renamed this section before (Connectors → Apps/Plugins). If the label differs, search settings for "developer mode". On Business/Enterprise workspaces an admin must allow custom connectors first.
Authorization
On first use ChatGPT opens the service's sign-in window. Sign in and approve access.
How to connect Rapidly to Cursor
The server address to paste into Cursor settings:
https://rapidly--leslie.run.tools
Fastest: click Open in Cursor below and confirm the prompt.
Manually:
- In Cursor open Settings → Cursor Settings → MCP and click Add new global MCP server.
- Paste the JSON copied below into
~/.cursor/mcp.json(per project:.cursor/mcp.jsonin the repo root). - Save the file. The server appears in the MCP list; authorize it there if asked.
Authorization
If the service needs sign-in, an authorize button appears next to the server in the MCP list.
Server tool list (7)
Raw names from tools/list. Only developers need these.
| test_idea | Save or resume one idea and advance it through Canvas, hypothesis, experiment options, recommendation, and a build prompt one durable stage at a time. A completed result returns the full copy-ready build_prompt before the detailed Canvas and experiment data. |
| find_ideas | Generate and save the requested number of ideas from one open brief. |
| list_ideas | Page through ideas in the team already authorised by this connection. |
| get_idea | Read one sprint-ready saved idea, including method artifacts, experiment sets, evidence, and advisory decisions. |
| record_test_result | Append customer-supplied experiment evidence, or append a correction without overwriting history. |
| decide_idea | Interpret current evidence and save a non-destructive advisory recommendation for one idea. |
| choose_next_idea | Compare the authorised team portfolio and identify the idea that most needs useful evidence next. |