Cursor setup
Cursor supports MCP servers, which is the best fit for Slideshot. Use Cursor’s MCP installer deeplink, then authorize Slideshot from the browser page Cursor opens.
1. Install the Slideshot MCP server
Click the button below to install the Slideshot MCP in Cursor:
Install Slideshot MCP in Cursor
The installer registers this MCP server:
- Name:
slideshot - URL:
https://api.slideshot.ai/mcp
2. Connect and authorize Slideshot
In Cursor, click Install and then Connect next to Slideshot MCP in the list.
Cursor opens an authorization page in your browser. Approve using Slideshot in Cursor. After approval, the Slideshot tools (create_run, get_run, list_runs, submit_run_input, list_run_artifacts, credentials, brand, feedback) appear in Cursor’s tool list.
3. Test the setup
Ask Cursor to record a small workflow against a public URL:
Create a Slideshot recording of
https://docs.slideshot.aithat walks through the docs landing page and the api-reference section.
Cursor calls create_run, polls get_run until status is succeeded, lists artifacts, and offers the demo.mp4 download URL.
Troubleshooting
- Deeplink does not open Cursor. Copy the
cursor://link above into your browser address bar, or open Cursor’s MCP settings and addhttps://api.slideshot.ai/mcpmanually with the nameslideshot. - MCP server not visible in chat. Make sure the server is enabled in Cursor’s settings and restart Cursor after the change.
- OAuth approval did not complete. Check that your browser allowed the redirect back to Cursor. Re-run the approval flow if it timed out.
- Tool calls fail with
401. Re-authorize the MCP connection. The refresh token may have expired. - Run paused with
awaiting_input. Ask Cursor to read the prompt and submit the requested value viasubmit_run_input.
Related
- Install skills: how to install the Slideshot skill across agents.
- MCP versus CLI: when to use the MCP server vs the CLI.
- Describe the demo flow: write prompts that produce sharper recordings.