Streams and playback
See which channels are live, start or stop a stream, and inspect or reorder what will play next.
Live Streaming Model Context Protocol (MCP)
Manage your Upstream live streams from the AI assistant you already use.
Upstream MCP is a live streaming MCP server for AI assistants. Check what is live, schedule broadcasts, organize media, tune playback, and prepare multistream destinations from ChatGPT, Claude, Claude Code, Kimi Code, VS Code, or your own integration.
Live streaming MCP, explained
A live streaming MCP server gives AI assistants tools for managing broadcasts.
Model Context Protocol (MCP) is an open standard that lets AI assistants discover and use tools. Once Upstream is connected, you can ask what is live, check whether media is ready, review a schedule, or propose a change without copying details between apps.
The Upstream MCP server turns those requests into authenticated actions through the Upstream live streaming API. It can check media processing, manage playback queues for 24/7 live streaming, update streams, configure automated live streaming schedules, and work with destinations for multistreaming. Confirmation behavior depends on your AI client and its settings.
Everyday live streaming tasks
Ask about the channel and make the change in the same conversation.
Use the Upstream MCP server to ask what is live, whether a video is ready, where a stream will publish, or what is next in the queue. Then use the relevant tool without hunting through separate screens.
Media and folders
Find videos, audio, images, and fonts; check processing; update details; and organize files into folders.
Schedules and destinations
Plan recurring broadcasts and manage where a stream publishes, including YouTube, Twitch, Kick, custom RTMP, and SRT.
Stream settings and organization
Review encoding, volume, recording, transitions, and video fit, then organize channels and campaigns with tags.
Complete broadcast workflows
Manage the whole broadcast, not just one setting.
Combine schedule, playback, media, and destination checks in one request. Ask for a plan first, then approve only the live streaming changes you want.
Schedule a 24/7 channel
Set scheduled starts and stops, repeat a broadcast, define continuous active and break periods, and preserve playback position between restarts.
Try asking
Inspect [stream name]. Propose a continuous schedule with 55 minutes live and a 5-minute break, preserve playback position, and wait for my approval before changing it.
Tune playback and output
Adjust resolution, frame rate, bitrate, recording, volume, loop or shuffle behavior, transitions, and how video fits the canvas.
Try asking
Show the current playback and output settings for [stream name]. Flag anything unusual and propose improvements without applying them.
Organize a growing media library
Search videos, audio, images, and fonts; check processing; update metadata; create folders; and organize multiple files together.
Try asking
Find processed media containing [keyword], show its current metadata and folders, then propose how to organize it. Do not move anything yet.
Prepare every destination
Create streams and manage YouTube, Twitch, Kick, custom RTMP, and SRT destinations, including whether they follow the stream schedule.
Try asking
Show every destination for [stream name] and which ones follow its schedule. Give me a preflight summary and wait for approval before changing anything.
Connect in three steps
Connect once, then start with a read-only check.
Add the Upstream MCP server, sign in with OAuth, and verify that it can see the right live streaming account before asking it to make changes.
- 01
Choose your AI client
Use the setup instructions below. ChatGPT, Claude, Claude Code, Kimi Code, and VS Code can connect through an Upstream OAuth sign-in screen.
- 02
Add the Upstream MCP server
Add the server URL, then sign in on studio.upstream.so and review the access request. No API key to copy.
- 03
Verify the connection
Ask the client to list your streams without making changes. If the client offers approval prompts, enable them before asking it to write or delete data.
Client setup
Choose the client you already use.
Use OAuth to connect ChatGPT, Claude, Claude Code, Kimi Code, or VS Code. Choose your client for setup steps, or use Other for connection details. API keys remain available as an alternative for scripts and clients without OAuth.
Already using an API key? Existing connections keep working. To switch to OAuth, remove the saved Authorization header or API-key setting, then reconnect and sign in.
Claude Code
OAuthAdd Upstream at user scope and sign in through your browser.
If Upstream is already configured with an API key, remove its Authorization header before signing in with OAuth.
Claude Code MCP guideTerminal
claude mcp add --transport http --scope user upstream \
https://studio.upstream.so/mcp- 1. Run the command shown here in your terminal.
- 2. Open Claude Code, run /mcp, and select Upstream to authenticate.
- 3. Sign in on studio.upstream.so, review the requested access, and approve the connection.
- 4. Run /mcp again to check the connection.
Remove access anytime in Upstream Profile → Connected apps.
ChatGPT
OAuthConnect through developer mode and sign in to Upstream. No API key to copy.
Developer mode availability depends on your account and workspace policy. This is a custom MCP connection; it does not require a published ChatGPT app.
ChatGPT connection guideMCP server URL
https://studio.upstream.so/mcp- 1. In ChatGPT, open Settings → Security and login and enable Developer mode.
- 2. Open Plugins, select the plus button, and name the connection Upstream.
- 3. Enter the MCP server URL shown here. Use OAuth for authentication when asked.
- 4. Sign in on studio.upstream.so, review the requested access, and approve the connection.
- 5. Start a new conversation and select the Upstream connection from the tools menu.
Remove access anytime in Upstream Profile → Connected apps.
Claude
OAuthAdd a remote custom connector and sign in to Upstream in your browser.
Custom connectors depend on your plan. On Team and Enterprise plans, an owner must add the connector before members can connect their own Upstream accounts.
Claude custom connector guideMCP server URL
https://studio.upstream.so/mcp- 1. Open Customize → Connectors in Claude.
- 2. Select the plus button, then Add custom connector.
- 3. Name it Upstream and enter the MCP server URL shown here. Add the connector and select Connect.
- 4. Sign in on studio.upstream.so, review the requested access, and approve the connection.
- 5. Enable Upstream from the Connectors menu in your conversation.
Remove access anytime in Upstream Profile → Connected apps.
Kimi Code
OAuthAdd the server URL and use Kimi Code’s browser sign-in flow.
You can also add the remote server interactively with /mcp-config.
Kimi Code MCP guide~/.kimi-code/mcp.json
{
"mcpServers": {
"upstream": {
"url": "https://studio.upstream.so/mcp"
}
}
}- 1. Add this server to ~/.kimi-code/mcp.json. Keep any other servers already in the file.
- 2. Start a new Kimi Code session and run /mcp-config login upstream.
- 3. Sign in on studio.upstream.so, review the requested access, and approve the connection.
- 4. Run /mcp to check the connection.
Remove access anytime in Upstream Profile → Connected apps.
VS Code
OAuthAdd Upstream to your user configuration and approve browser sign-in.
VS Code discovers the OAuth settings automatically. No API key or client secret is needed.
VS Code MCP guidemcp.json
{
"servers": {
"upstream": {
"type": "http",
"url": "https://studio.upstream.so/mcp"
}
}
}- 1. Run MCP: Open User Configuration from the Command Palette.
- 2. Add this server to mcp.json. Keep any other servers already in the file.
- 3. Start Upstream from the server configuration and follow the authentication prompt.
- 4. Sign in on studio.upstream.so, review the requested access, and approve the connection.
Remove access anytime in Upstream Profile → Connected apps.
Other MCP clients
Check compatibilityUse these details if your client supports remote Streamable HTTP servers with OAuth or custom request headers.
- 1. Open your client's MCP or integrations settings.
- 2. Add a remote HTTP server using the details shown.
- 3. Follow the OAuth sign-in flow if supported, or store a dedicated API key in the client's secret settings.
- 4. Reconnect, then confirm that the client discovers Upstream's tools.
Connection details
Transport: Streamable HTTP
Endpoint: https://studio.upstream.so/mcp
Authentication: OAuth (recommended)Use OAuth discovery when your client supports it. Callback support varies by client; check its guide if sign-in fails. For scripts or clients without OAuth, use the API-key alternative below.
API-key alternative
For scripts or clients without OAuth, create a dedicated key in Upstream Profile → API Keys. Use the same server URL and store this header in the client’s secret settings, replacing the placeholder with your key.
API-key request header
Authorization: Bearer YOUR_API_TOKENNever paste a real API key into a shared file, public repository, support ticket, prompt, or directory submission. Revoke unused keys from Profile → API Keys.
Developer resources
Build directly with the same Upstream live streaming API.
The Upstream MCP tools use the customer API for streams, media, queues, folders, tags, and destinations. Read the server definition and client configuration on GitHub, browse the REST API reference, or download a machine-readable specification for your own integration.
These resources are public and contain no customer data or API keys. Calling the API or MCP tools still requires authentication.
FAQ
Upstream MCP and live streaming MCP questions
What a live streaming MCP server is, what Upstream MCP can do, which clients work, and how to connect safely.
Upstream MCP is a remote live streaming MCP server. It connects an MCP-compatible AI assistant to authenticated tools for managing Upstream streams, schedules, playback queues, media, folders, tags, and multistream destinations.
Manage your next broadcast from the AI client you already use.
Connect the Upstream live streaming MCP server with OAuth or a dedicated API key, then start with a read-only check. Then schedule broadcasts, organize media, tune playback, and prepare destinations from the same conversation.