pagent

io.github.aihuminPublished by GitHub account aihuminv1.0.1Updated Oct 30, 2026

A/B testing MCP server for pagent: create, run and review A/B tests on your live website.

VerifiedStreamable HTTPWeb executableData & AnalyticsBusiness & Commerce

Overview

AI-generated overview

Hosted pagent MCP server that lets an assistant read, create and control A/B tests on your live website.

What you can do
  • List running and completed tests and read their Bayesian results
  • Compare tests and inspect what each variation changes on the page
  • Read pages, audiences, conversion goals, personas and guidelines
  • Capture a hypothesis and turn it into a test
  • Start, pause, resume, queue, stop, evolve or roll back tests
  • Create pages and conversion goals and manage audiences
When to use it
Useful when your team runs A/B tests on a live site through pagent and wants to ask about winners, compare past tests, or start and pause experiments from the chat client instead of the pagent dashboard.
Requirements
Remote Streamable HTTP endpoint at app.pagent.ai with OAuth 2.0 sign-in (or a personal token). A pagent account with owner or administrator access to the organisation, MCP enabled for it, and the pagent script installed on the website. The optional CLI setup runs via npx and needs Node.js.
Before you install
Write access lets the assistant create pages and goals, manage audiences, and start, pause, stop, evolve or roll back live tests; choose read-only access unless you need changes. Access is scoped to organisations chosen at sign-in and can be revoked in pagent settings. Tests run on your live site, so variations affect real visitors.

Installation

In SourceWeft

  1. Open pagent 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/io.github.aihumin%2Fpagent/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": {
    "pagent": {
      "type": "http",
      "url": "https://app.pagent.ai/api/mcp"
    }
  }
}

README

pagent: the A/B testing MCP server for coding agents

@pagent/mcp connects Claude, ChatGPT, Claude Code, Codex, Cursor and any other MCP client to pagent, so your agent can run A/B tests on your live website. Set it up in one command:

bash
npx @pagent/mcp init

This finds the MCP clients on your machine and points them at pagent's hosted MCP server. Nothing else to copy, no config format to choose.

What pagent is

pagent is an AI A/B testing agent, an AI Experiment Engineer for your website. It reads your pages, writes the hypothesis, builds the variation as real code on your design system, runs the test on your live site with Bayesian statistics, and learns what to try next. Your team reviews each variation before it goes live. pagent adds to your testing stack; it does not replace it.

With this MCP server your agent joins that loop: it reads results, captures the next hypothesis, and starts the next test from the chat you already use.

Can Claude or ChatGPT run A/B tests on my live website?

Yes, once they are connected to an experimentation platform through MCP. A language model on its own cannot serve variations to your visitors or measure conversions. With the pagent MCP server, Claude, ChatGPT or your coding agent can start, pause and stop tests on your live site and read their results, while pagent builds the variations, splits the traffic and runs the statistics.

Things you can ask once connected:

  • "Which of our running A/B tests is winning, and how sure are we?"
  • "Compare last month's pricing page tests and tell me what changed on the page."
  • "Capture a hypothesis: a shorter signup form will raise trial starts. Turn it into a test."
  • "Pause the checkout test and roll it back."

What your agent can do

With read access:

  • List running and completed tests and read their Bayesian results
  • Compare tests and inspect what each variation changes on the page
  • Read pages, audiences, conversion goals, personas and guidelines

With write access:

  • Capture a hypothesis and turn it into a test
  • Start, pause, resume, queue, stop, evolve or roll back a test
  • Create pages and conversion goals, manage audiences

You choose read or write, and which organisations the client may see, during sign-in. You can revoke a connection at any time in your pagent settings.

Usage

bash
npx @pagent/mcp init                 # detect your clients and connect themnpx @pagent/mcp init --client cursor # connect one clientnpx @pagent/mcp init --local         # write a project config, not a user onenpx @pagent/mcp init --dry-run       # show what would change, write nothingnpx @pagent/mcp print                # print the config without writingnpx @pagent/mcp list                 # list supported clients

Supported clients

ClientHow it is configured
Claude Codeclaude mcp add
Codexcodex mcp add
Cursor~/.cursor/mcp.json or .cursor/mcp.json
VS Code.vscode/mcp.json
Windsurf~/.codeium/windsurf/mcp_config.json
Zed~/.config/zed/settings.json
Claude (web and desktop)Settings, Connectors, add a custom connector
ChatGPTDeveloper mode, Plugins, add a custom connector

Claude and ChatGPT are configured in their own interface, so this CLI prints the steps rather than editing anything. Run npx @pagent/mcp print --client chatgpt.

Existing servers in your config are left alone. If a config file cannot be parsed, for example because it has comments, the CLI prints the entry for you to paste instead of rewriting the file.

Connecting by hand

Any MCP client can use the hosted server directly:

  • Endpoint: https://app.pagent.ai/api/mcp
  • Transport: Streamable HTTP
  • Authentication: OAuth 2.0, or a personal token from AI client access

Before you connect

You need a pagent account with owner or administrator access to the organisation, MCP enabled for it, and a website with the pagent script installed so there are tests and visitor data to read.

Links

License

MIT. pagent itself is a commercial product; this CLI only writes local configuration files.

Source: README.md at commit cbb5f32

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

2
  1. v1.0.1LatestOct 23, 2026
  2. v1.0.0Sep 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