What transport protocols are supported for media streams?
The platform supports RTSP and RTMP protocols for real‑time video streams.

@qianlima365
Basic information
基于ONVIF协议的设备控制MCP
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"onvif-mcp": {
"command": "python",
"args": [
"run",
"main.py",
"--host",
"0.0.0.0",
"--port",
"8020"
]
}
}
}Tool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
ONVIF MCP is a device control and management platform (Media Control Platform) based on the ONVIF protocol. It provides standardized control interfaces for network audio/video devices such as IP cameras and NVRs. It is intended for users who need to discover, configure, and control ONVIF-compliant devices.
Start the service using the CLI tool with the command mcp dev main.py or by running python run main.py --host 0.0.0.0 --port 8020. No installation instructions are provided in the README.
The platform supports RTSP and RTMP protocols for real‑time video streams.
ONVIF MCP is implemented in Python.
It uses ONVIF WS‑Discovery for device discovery and SOAP for control interactions.
Run the command `mcp dev main.py` or `python run main.py --host 0.0.0.0 --port 8020`.
The README does not list specific dependencies, but the implementation relies on Python and ONVIF standards (WS‑Discovery, SOAP).
A curated list of references for MLOps

Soar Flight Booking MCP is a remote MCP server available at https://mcp.soar.flights.
YC (S26) | Open Computer History | Continuously record your company computer work, map your workflows, help you find work worth automating, and power your agents' context
🚀 The fast, Pythonic way to build MCP servers and clients.

A good sequence diagram can solve almost any communication problem in engineering. Volley lets your agent write them as plain text, with the real request and response payloads on every arrow. It checks its own syntax wi
Comments