# MCP Servers with a list_experiments tool Every MCP server Pod knows of that exposes a list_experiments tool. 8 servers, ordered by decision readiness and adoption — GitHub stars and npm downloads where available, then reported issue volume. Pod has connected to 8 of them; the rest are publisher-reported and unverified. ## [AIOProductOS](/mcp/aioproductos) AIOProductOS is a product operating system: one shared record per customer that joins revenue, feedback, product analytics, delivery work, and code. Most product stacks keep those in four tools that never meet, so "which accounts asked for this, and what are they worth?" takes a spreadsheet and an afternoon. Here it is one call. This connector puts that spine in your assistant — 71 tools, 34 read and 37 write. Read: the board and backlog; features, initiatives, OKRs, ideas, sprints, releases, decisions, experiments and Pages; customer insights and the Weekly Signal Memo; the support inbox, team channels and bookings; the identity graph; a live map of your codebase; and revenue-weighted analytics — NPS, NRR, funnels, retention, path analysis, roadmap drift, customer 360. Write: create and update anything on that ladder, comment, capture insights, reply in the support inbox, post to channels, and move work through sprints — so you finish the job in chat instead of switching back to a web UI. Three tools render an interactive app right in the conversation rather than a wall of JSON. Ask for your board and you get it grouped by status — change a status in the card and it writes back through update_task. Ask for the weekly memo and each theme carries the evidence behind it; one click turns a theme into a task linked to its feature. Ask for a funnel and you get conversion per step with the live MRR standing behind each one — the product-to-subscription join that only exists when both live on one record. Everything is scoped to your organization and your role's permissions. One tool is destructive — delete_task — and it requires an explicit confirmation argument, so it can never fire on a task id alone. 0 GitHub stars · 70 tools reported — Live. Answered with 71 tools. ## [www.rapidly.co](/mcp/www-rapidly-co) Test the idea before you build it. Rapidly works inside your AI agent. Bring an idea you already have, or ask Rapidly to generate one from a company website. In about five minutes, Rapidly turns it into a Lean Canvas, a measurable hypothesis and pass mark, then designs practical Pretotyping experiments. The result is a copy-ready build prompt for the smallest experiment worth running. Your agent builds the test. Real customers provide the evidence. The work is also saved in your Rapidly workspace so you can review it, continue it and record the result. 2 GitHub stars · 21 tools reported — Live, but requires authorization before it will list tools. Publisher lists 21 tools. ## [ABConvert](/mcp/abconvert) ABConvert helps Shopify merchants inspect experiment performance, compare results, create draft tests, preview storefront changes, and manage experiment lifecycles through Claude. 33 tools reported — Live, but requires authorization before it will list tools. Publisher lists 33 tools. ## [elluminate](/mcp/elluminate) The elluminate MCP server allows to connect to the elluminate platform, upload data, create new models, collections and criteria and run experiments. Agents can autonomously evaluate any AI model, agent or system through the MCP Server. 45 tools reported — Live, but requires authorization before it will list tools. Publisher lists 45 tools. ## [Intelligems](/mcp/intelligems) Intelligems helps Shopify brands run A/B tests on pricing, content, and site experiences to maximize revenue and profit. The MCP connector lets you analyze experiments, explore customer segments, and even create new A/B tests directly from Claude. Whether you're an agency reviewing client performance or a brand operator checking test results, Intelligems brings your full testing and analytics workflow into one conversation — so you can spot trends, compare segments, and plan your next test faster, with less context-switching. 50 tools reported — Live, but requires authorization before it will list tools. Publisher lists 50 tools. ## [Scispot.io](/mcp/scispot-io) Scispot is built for high-throughput labs such as molecular diagnostics labs, CROs, and CDMOs, as well as AI-driven biotech companies where speed, traceability, and compliance must work together. Teams can run AI directly in production workflows without exporting data or breaking audit trails. 0 GitHub stars · 34 tools reported — Live, but requires authorization before it will list tools. Publisher lists 34 tools. ## [Shogun](/mcp/shogun) Shogun A/B Testing enables conversion rate optimization for Shopify stores — and this connector gives Claude the whole loop, from the first idea to the promoted winner. Ask what's running, and Claude lists your live, paused and draft experiments. Ask how a test is doing, and it returns per-variant metrics, attributed order aggregates and the Bayesian statistics Shogun uses to call a winner — not a screenshot of a dashboard, but the underlying numbers, so you can ask follow-up questions like ""was that lift real on mobile?"" or ""what did it look like for paid social traffic only?"" Claude can also build the test. Describe what you want to try and it drafts the experiment: eight test types (page, template, theme, URL redirect, price, product details, checkout and shipping), eight goal metrics including revenue per visitor and profit per visitor, traffic splits, and audience targeting by device, login state, B2B, new-versus-returning, location, URL or referrer. Drafts stay drafts until you start them, and they open in the Shogun app exactly as Claude left them, so nothing goes live without a person saying so. Beyond experiments, the connector reports storewide and optimized-traffic KPIs, product-level analytics, and ranked testing recommendations — all filterable by date range, device, traffic source and ad campaign — plus the Shopify resources a test is built from: products, collections, pages, templates, themes, audiences and shipping profiles. Agencies and multi-store brands can switch the active store mid-conversation, so one connection covers every shop on the account. Every write is scoped and explicit: destructive actions require confirmation, drafts are separate from running tests, and each change is recorded in Shogun's audit log. Order data is returned as PII-stripped aggregates; raw shop event details are never exposed. Requires a Shopify store with the Shogun A/B Testing app installed. 26 tools reported — Live, but requires authorization before it will list tools. Publisher lists 26 tools. ## [Varify MCP](/mcp/varify-mcp) Varify MCP connects Claude to your Varify.io A/B testing account, letting you manage experiments directly through conversation. Create new experiments and variations, or edit, duplicate, pause, and archive existing ones. Adjust traffic allocation between variants and define page and audience targeting by URL, device, browser, or UTM parameters. Turn tracking on or off per experiment. If GA4 is connected, view results directly, including daily reports and revenue analyses based on GA4 data. Agencies get an overview of all managed client accounts in one place. The MCP uses the same public API available for custom integrations. 12 tools reported — Live, but requires authorization before it will list tools. Publisher lists 12 tools. ## For agents This page has a [Markdown](/mcp/tool/list-experiments.md) and a [JSON](/mcp/tool/list-experiments.json) twin. Pod is also queryable over MCP at `https://api.askpod.ai/mcp/read`.