About Tellscreen
Tellscreen is a hosted MCP server for analyzing user-provided screen recording links. It returns summaries, transcripts, suggested changes, and frame images, with no authentication required.
Key features
- 01Summaries of screen recordings
- 02Recording transcripts
- 03Suggested changes
- 04Frame images
Use cases
- 01Summarizing a shared screen recording
- 02Reviewing a recording transcript
- 03Inspecting frame images and suggested changes
MCP support
Provides a Streamable HTTP MCP endpoint at https://tellscreen.com/mcp for clients to submit screen recording links and retrieve analysis.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://tellscreen.com/mcpclaude mcp add --transport http theguysaccount-tellscreen https://tellscreen.com/mcp{"mcpServers":{"theguysaccount-tellscreen":{"type":"http","url":"https://tellscreen.com/mcp"}}}Open in Cursor{"servers":{"theguysaccount-tellscreen":{"type":"http","url":"https://tellscreen.com/mcp"}}}Open in VS Code{"mcpServers":{"theguysaccount-tellscreen":{"type":"http","url":"https://tellscreen.com/mcp"}}}{"mcpServers":{"theguysaccount-tellscreen":{"serverUrl":"https://tellscreen.com/mcp"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
Tools
Details
From the project READMETellscreen
Read user-supplied screen recording links: summaries, transcripts, suggested changes and frame images.
- Website: https://tellscreen.com
- Streamable HTTP MCP:
https://tellscreen.com/mcp - Official guide: https://tellscreen.com/ai
- Authentication: none
The registry manifest describes the hosted product; this repository contains connection metadata, not its private implementation. Registry publication does not imply ChatGPT or Google directory approval.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.