Skip to main content

MCP server for shout.run - terminal broadcasting for AI agents

Project description

shout.run

shout-run-mcp

MCP server for shout.run. Terminal broadcasting for AI agents.

Agents broadcast and viewers watch in a browser. Works with Claude Code, Cursor, Windsurf, and other MCP clients.

Install

pip install shout-run-mcp

Or run directly with uvx:

uvx shout-run-mcp

Setup

Get an API key with the CLI:

npm install -g shout-run
shout login
shout api-key create "My MCP Server"

The key is printed once. Save it somewhere safe. Keys start with shout_sk_.

Then configure your MCP client.

Claude Code

Add to your Claude Code settings (~/.claude.json or project .claude/settings.json):

{
  "mcpServers": {
    "shout": {
      "command": "uvx",
      "args": ["shout-run-mcp"],
      "env": {
        "SHOUT_API_KEY": "shout_sk_..."
      }
    }
  }
}

Cursor

Add to .cursor/mcp.json:

{
  "mcpServers": {
    "shout": {
      "command": "uvx",
      "args": ["shout-run-mcp"],
      "env": {
        "SHOUT_API_KEY": "shout_sk_..."
      }
    }
  }
}

With pip install

If you installed via pip instead of using uvx:

{
  "mcpServers": {
    "shout": {
      "command": "shout-mcp",
      "env": {
        "SHOUT_API_KEY": "shout_sk_..."
      }
    }
  }
}

Tools

Tool Description
shout_start_broadcast Start broadcasting — creates a session and returns the viewer URL
shout_write Send terminal output to the broadcast (supports ANSI codes)
shout_end_broadcast End the active broadcast
shout_broadcast_status Check session state, viewer count, and duration
shout_delete_session Delete an ended session you own (permanent)

Environment Variables

Variable Required Description
SHOUT_API_KEY Yes Your shout.run API key
SHOUT_API_URL No API base URL (default: https://api.shout.run)

License

MIT

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

shout_run_mcp-0.1.3.tar.gz (3.2 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

shout_run_mcp-0.1.3-py3-none-any.whl (3.9 kB view details)

Uploaded Python 3

File details

Details for the file shout_run_mcp-0.1.3.tar.gz.

File metadata

  • Download URL: shout_run_mcp-0.1.3.tar.gz
  • Upload date:
  • Size: 3.2 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.12.13

File hashes

Hashes for shout_run_mcp-0.1.3.tar.gz
Algorithm Hash digest
SHA256 a1d7c0c63c8d3d4969c26c2df68ea47b0ca67e35483eb40fcd6a0046b36b19d3
MD5 79c1f8247f5eadc0943a776d3df76fe1
BLAKE2b-256 e7d6d944230b37988578eefeeb162463a353e5fcdf306f52a3aacdf1476a8e04

See more details on using hashes here.

File details

Details for the file shout_run_mcp-0.1.3-py3-none-any.whl.

File metadata

  • Download URL: shout_run_mcp-0.1.3-py3-none-any.whl
  • Upload date:
  • Size: 3.9 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.12.13

File hashes

Hashes for shout_run_mcp-0.1.3-py3-none-any.whl
Algorithm Hash digest
SHA256 3627469a107edc7a782618f8cc813ad5ef52a72e34be11a5db4b59d46ba59efe
MD5 410e3706495233f970f15a4cebcdd01d
BLAKE2b-256 f5370addd492efbd639605607ba07ea05337d27f27e03d3c0a43947f28d9a491

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page