Rapidly

co.rapidlyPublished by rapidly.coOfficial publisherv2.0.0Updated Oct 24, 2026

Test the idea before you build it. Rapidly works inside your AI agent.

VerifiedStreamable HTTPWeb executableProductivity & WorkflowKnowledge & MemoryBusiness & Commerce

Overview

AI-generated overview

Rapidly runs a pretotyping workflow inside an AI agent: it turns an idea into a Lean Canvas, a measurable hypothesis and small experiments with a build prompt.

What you can do
  • Save an idea and build its full Lean Canvas
  • Turn the riskiest assumption into a measurable hypothesis and research a pass threshold
  • Save three to five experiment options, recommend a first test and generate one build prompt
  • Generate grounded ideas from a company name and website, with sources
  • Keep results saved in a Rapidly team so a run can be resumed or reviewed later
When to use it
Useful when you want to validate a product or business idea cheaply before building it, and want the method, canvas, hypothesis and experiment design handled consistently rather than improvised in chat. Also fits when you want ideas generated from a company website and taken through the same method.
Requirements
A remote MCP endpoint; no local package. OAuth sign-in with a Rapidly account and team selection, or a personal token for agents without OAuth. A Rapidly account is created with name, email and team name if you are new. Usage limits apply: five new ideas on a trial, ten ideas per paid seat per month.
Before you install
Sign-in grants the server access to your Rapidly team workspace, and ideas and results are saved there rather than staying in the chat. A personal token is shown once and should be kept out of chat and project files. Generated facts, cited sources and proposed pass marks are proposals needing human review, not measured results. Paid plans and per-seat idea limits involve billing.

Installation

In SourceWeft

  1. Open Rapidly in the dashboard and add it to a workspace.
  2. Connect the required credentials. They are stored privately and never shown on public pages.
  3. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/co.rapidly%2Frapidly/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config. The client completes OAuth sign-in on first connect.

{
  "mcpServers": {
    "rapidly": {
      "type": "http",
      "url": "https://www.rapidly.co/mcp"
    }
  }
}

README

Rapidly MCP

Test the idea before you build it

Rapidly 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.

Rapidly 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.

Rapidly MCP is generally available.

Version 2.0.0 is published in the official MCP Registry.

Works with Claude, Codex, ChatGPT and Hermes. OpenClaw, Grokbot and other agents can also use Rapidly if they support remote MCP.

Connect Rapidly · Let your agent set it up · Manual setup

Here's what a first run looks like

A suburban independent bookshop wants to grow weekday foot traffic and build a younger, regular customer base.

Rapidly 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.

Rapidly 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%.

[The Third-Place Pass landing page built from Rapidly's recommended Fake Door experiment.]

See the complete Rapidly run · Open the customer-facing landing page

This was a demonstration for a hypothetical bookshop. The pass mark was a proposal to test, not a measured result. No customer results are claimed.

Why can't I just ask Claude or Codex?

You can. We do. The answer will probably look reasonable.

Rapidly is useful because the method is already there. For one idea, the core run:

  1. saves the idea and builds its full Lean Canvas;
  2. turns the riskiest assumption into a measurable hypothesis and researches the pass threshold;
  3. saves three to five complete experiment options, recommends the easiest credible first test and generates one build prompt for that recommendation.

Your 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.

Successful 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.

The method combines Alberto Savoia's Pretotyping with our own practice through 4,000+ experiments with client teams and 200+ workshops.

Install the Rapidly plugin

The plugin bundles the Rapidly MCP connection with four skills that tell your agent when and how to use it: test an idea, record a test result, choose the next idea, and setup.

In Claude Code:

text
/plugin marketplace add Exponentially-Platform/Rapidly-MCP/plugin install rapidly@rapidly

Then run /mcp, choose Rapidly and sign in.

In Codex:

bash
codex plugin marketplace add Exponentially-Platform/Rapidly-MCP

Then open the Plugins Directory in the ChatGPT desktop app or Codex, choose the Rapidly marketplace and install Rapidly. Sign in when Rapidly asks.

In Cursor, the repository carries a Cursor marketplace manifest that points at the same plugin. Install Rapidly from the Cursor marketplace once it is listed, then sign in when Rapidly asks.

The plugin lives in plugins/rapidly. scripts/package-openai-plugin.sh builds the ZIP for OpenAI's plugin directory. The ZIP takes the published plugin's package name and drops mcp.json's auth block, because OpenAI requires both for an update. An optional second argument merges the reviewer test cases and release notes, which are kept outside this public repo.

Connect Rapidly

If you're new to Rapidly

Open rapidly.co/rapidly-mcp and enter your name, email and team name. Rapidly creates the account and team, then shows your personal token once.

The 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.

If you already use Rapidly

Connect with OAuth, choose your Rapidly team and approve access. You don't need to create another account or personal token.

The exact steps differ between Codex, Claude and ChatGPT. Use the setup instructions for your agent.

If you're using another agent

Give your agent this address and ask it to connect Rapidly:

text
https://www.rapidly.co/mcp

Use OAuth if the agent supports it. Otherwise, follow the agent setup instructions to keep your personal token out of chat and project files.

Start with an idea

To generate three ideas and fully test all three in one request:

text
Ask Rapidly for three ideas for [company], focused on [opportunity], and fully test all three in one go.

Rapidly 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.

Use one you already have:

text
Ask Rapidly to test this idea: [describe the customer, problem and proposed change].

Or ask Rapidly to generate one from a company and its website:

text
Ask Rapidly to generate [one or more] ideas for [company name] using [website URL]. Focus on [optional customer, problem or opportunity].

Rapidly 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.

Rapidly 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.

By the end, you should have:

  • sources you can open and facts you can review;
  • a full Lean Canvas;
  • a measurable hypothesis and decision rule suited to the idea's riskiest assumption;
  • three to five saved experiment options, GO and NO-GO rules, and a recommended first experiment;
  • one build prompt for the recommended test asset.

Review the output, ask your agent to build the asset, then put the test in front of real customers.

See more example prompts

Help us improve Rapidly MCP

We're looking for the points where this becomes confusing or stops being useful.

After your run, please tell us:

  • Did the connection work the first time?
  • Where did you hesitate or get stuck?
  • Was the proposed experiment small enough to run?
  • What did you keep, and did it change what you planned to do next?

Email [email protected] 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.

Current limits

  • A trial includes five new ideas. Taking one idea through its Canvas, hypothesis and experiments still counts as one idea.
  • Paid plans include ten ideas per paid seat per calendar month.
  • Need more? Email [email protected] to discuss the right next step for your team.
  • Generated facts, cited sources and proposed targets need human review before use.

Guides

Source: README.md at commit d8473c2

Tools

0
This server asks you to sign in, so SourceWeft could not read its tools without an account and has not indexed them. What a connected account sees can depend on that account and its permissions.

Version history

1
  1. v2.0.0LatestSep 16, 2026

Score

85% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts