# AI use cases for Superpower (stloendays/Superpower) Repo: [stloendays/Superpower](https://github.com/stloendays/Superpower) | Use cases: 4 | Page: https://dedupedai.com/use-cases/stloendays-superpower/ Superpower is a browser extension and Windows desktop app that lets AI web chats and a native workspace call local or remote MCP tools and return the results to the same conversation. This file holds every use case of this repo. Each one starts with a "## " heading and ends with its URL. - Summarize a web page inside your AI chat: https://dedupedai.com/use-cases/stloendays-superpower/summarize-page-in-ai-chat/ - Build research Projects from saved web and YouTube sources: https://dedupedai.com/use-cases/stloendays-superpower/build-research-projects-from-saved-sources/ - Send a research set to a notes or file MCP tool: https://dedupedai.com/use-cases/stloendays-superpower/hand-research-to-notes-mcp-tool/ - Run MCP actions from a native Windows workspace: https://dedupedai.com/use-cases/stloendays-superpower/run-mcp-actions-from-desktop-workspace/ ## How to summarize a web page inside your AI chat with Superpower Repo: [stloendays/Superpower](https://github.com/stloendays/Superpower) | Difficulty: Intermediate | Time: 45 minutes | Basis: From the README Send a page or selection to Copilot and get a structured summary in the same AI chat. **Who it is for:** A researcher or analyst reading long articles who wants the summary inside the AI chat they already use. **The problem:** Copying page text into a chat by hand is slow, and the chat cannot reach your own MCP tools on its own. **The outcome:** A summary of the selected text or page appears in the active AI conversation, with any MCP tool results returned to the same chat. ### Steps 1. Install Superpower from the Chrome Web Store. 2. Open the extension settings and add an MCP connection using Streamable HTTP with http://localhost:3006/mcp. 3. Open a supported AI website and check that the sidebar opens to Copilot. 4. Open an ordinary web page, select text, and use the Page Assistant to choose Summarize. 5. Read the result in the AI composer and check that the tool results match the source page. ### Prompt to paste into your agent ```text Using the Superpower repo at https://github.com/stloendays/Superpower, set up the browser extension with a Streamable HTTP connection to http://localhost:3006/mcp, then summarize the selected text on in the Copilot workspace. Expected output: a structured summary in the AI chat. Verify that the summary cites points that appear on the source page. ``` ### Caveat The README does not say how to start the local proxy at localhost:3006, so you need your own MCP server running there before the first run. Risk, credentials: The MCP endpoint and any tools behind it may use your own accounts, so only point Superpower at servers you trust. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/stloendays-superpower/summarize-page-in-ai-chat/ ## How to build research Projects from saved web and YouTube sources with Superpower Repo: [stloendays/Superpower](https://github.com/stloendays/Superpower) | Difficulty: Intermediate | Time: 30 minutes | Basis: From the README Save selected text and video summaries to Knowledge, group them into Projects, and synthesize them. **Who it is for:** A student or research analyst collecting sources across several topics who needs them grouped and reusable. **The problem:** Sources saved in separate tabs or notes are hard to reuse, and duplicating them across topics creates clutter. **The outcome:** A Knowledge Project holds the sources for one topic, can be attached to Ask, and can be synthesized or exported as Markdown. ### Steps 1. Open a web page or a YouTube watch page and select the text you want to keep. 2. Use the Page Assistant to Save to Knowledge, or use Summarize video on a YouTube watch page. 3. In Copilot, open the Knowledge list, filter by source type, and select the items you need. 4. Create a Knowledge Project and add the selected items to it. 5. Open the Project and use Ask, synthesize, or export to Markdown on the whole group. ### Prompt to paste into your agent ```text Using the Superpower repo at https://github.com/stloendays/Superpower, save the selected sources on to Knowledge, add them to a Project named , and export the Project as Markdown. Expected output: one Markdown file that lists each source with its title and URL. Verify that every source in the file has a URL and a timestamp. ``` ### Caveat YouTube summaries use loaded transcript segments when they are available and fall back to supplied video metadata otherwise, so summary quality depends on what the page loads. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/stloendays-superpower/build-research-projects-from-saved-sources/ ## How to send a research set to a notes or file MCP tool with Superpower Repo: [stloendays/Superpower](https://github.com/stloendays/Superpower) | Difficulty: Advanced | Time: 1 hour | Basis: From the README Hand a Knowledge Project to a compatible notes or file tool through the review-first path. **Who it is for:** A team member who keeps shared notes in a file or notes service and wants research sent there without copy and paste. **The problem:** Moving collected sources into a shared notes or file store is manual, and automated writes can be risky without review. **The outcome:** A compatible notes or file tool receives the Project content after you review the action, with the result returned to the chat. ### Steps 1. Connect a notes or file MCP tool in Superpower, such as one for Notion or Drive if your server provides it. 2. Open Copilot and confirm the tool appears under Connected Actions. 3. Select a Knowledge Project and choose the handoff to the MCP destination. 4. Review the parameters and the confirmation prompt before the action runs. 5. Check the saved item in the destination tool and note any errors shown in the chat. ### Prompt to paste into your agent ```text Using the Superpower repo at https://github.com/stloendays/Superpower, hand the Knowledge Project to the connected notes MCP tool through the review-first path. Expected output: a confirmed write in the destination with a result message in the chat. Verify that the destination item contains each source URL from the Project. ``` ### Caveat Superpower does not replay a tool request after a timeout or ambiguous failure, so check the destination for a partial write before you retry. Risk, credentials: The destination tool writes to your real notes or file account, so check the review prompt and the target before you confirm. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/stloendays-superpower/hand-research-to-notes-mcp-tool/ ## How to run MCP actions from a native Windows workspace with Superpower Repo: [stloendays/Superpower](https://github.com/stloendays/Superpower) | Difficulty: Intermediate | Time: 45 minutes | Basis: From the README Manage MCP connections, apps, actions and runs from the Qt desktop app. **Who it is for:** A Windows user who wants a dedicated control surface for MCP tools instead of working inside a browser chat. **The problem:** Managing several MCP connections and their actions from a browser chat is awkward, and there is no dedicated run history. **The outcome:** Connections, apps, actions and runs are visible in one desktop workspace, with guarded execution of each action. ### Steps 1. Download the portable Windows package from the GitHub Releases page for the Superpower repo. 2. Extract the package and launch the desktop app. 3. Add an MCP connection under Connections. 4. Open Apps and Actions to choose the tool you want to run. 5. Review the action in workflow review, run it, and check the entry under Runs. ### Prompt to paste into your agent ```text Using the Superpower repo at https://github.com/stloendays/Superpower, download the latest portable Windows package from GitHub Releases, connect it to the MCP server at , and run the action from the Actions view. Expected output: a completed entry in Runs with its result. Verify that the Runs entry shows the same tool name and status as the review step. ``` ### Caveat The README describes the desktop app as a portable Windows package, so it is not the path for Mac or Linux users. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/stloendays-superpower/run-mcp-actions-from-desktop-workspace/